Fix CI failures: correct context window ratio and remove unused imports

- Fix test expectations to use 0.85 ratio instead of 0.75 (matches CONTEXT_WINDOW_USAGE_RATIO)
- Remove unused imports (pytest, Mock) from test file
- Add context window size warning for large models (>100K tokens)
- Update documentation with performance considerations and rate limiting best practices
- Address code review feedback from João regarding validation and error handling

Co-Authored-By: João <joao@crewai.com>

.github/workflows/linter.yml

@@ -30,4 +30,7 @@ jobs:
       - name: Run Ruff on Changed Files
         if: ${{ steps.changed-files.outputs.files != '' }}
         run: |
-          echo "${{ steps.changed-files.outputs.files }}" | tr " " "\n" | xargs -I{} ruff check "{}"
+          echo "${{ steps.changed-files.outputs.files }}" \
+            | tr ' ' '\n' \
+            | grep -v 'src/crewai/cli/templates/' \
+            | xargs -I{} ruff check "{}"

.github/workflows/tests.yml

@@ -14,7 +14,7 @@ jobs:
     timeout-minutes: 15
     strategy:
       matrix:
-        python-version: ['3.10', '3.11', '3.12']
+        python-version: ['3.10', '3.11', '3.12', '3.13']
     steps:
       - name: Checkout code
         uses: actions/checkout@v4

README.md

@@ -403,7 +403,7 @@ In addition to the sequential process, you can use the hierarchical process, whi
 
 ## Key Features
 
-CrewAI stands apart as a lean, standalone, high-performance framework delivering simplicity, flexibility, and precise control—free from the complexity and limitations found in other agent frameworks.
+CrewAI stands apart as a lean, standalone, high-performance multi-AI Agent framework delivering simplicity, flexibility, and precise control—free from the complexity and limitations found in other agent frameworks.
 
 - **Standalone & Lean**: Completely independent from other frameworks like LangChain, offering faster execution and lighter resource demands.
 - **Flexible & Precise**: Easily orchestrate autonomous agents through intuitive [Crews](https://docs.crewai.com/concepts/crews) or precise [Flows](https://docs.crewai.com/concepts/flows), achieving perfect balance for your needs.
@@ -546,7 +546,7 @@ This example demonstrates how to:
 
 ## Connecting Your Crew to a Model
 
-CrewAI supports using various LLMs through a variety of connection options. By default your agents will use the OpenAI API when querying the model. However, there are several other ways to allow your agents to connect to models. For example, you can configure your agents to use a local model via the Ollama tool.
+CrewAI supports using various LLMs through a variety of connection options. By default your agents will use the OpenAI API when querying the model. However, there are several other ways to allow your agents to connect to models. For example, you can configure your agents to use a local model via the Ollama tool, or access 300+ AI models through AI/ML API.
 
 Please refer to the [Connect CrewAI to LLMs](https://docs.crewai.com/how-to/LLM-Connections/) page for details on configuring your agents' connections to models.
 
@@ -706,7 +706,7 @@ A: Yes. CrewAI excels at both simple and highly complex real-world scenarios, of
 
 ### Q: Can I use CrewAI with local AI models?
 
-A: Absolutely! CrewAI supports various language models, including local ones. Tools like Ollama and LM Studio allow seamless integration. Check the [LLM Connections documentation](https://docs.crewai.com/how-to/LLM-Connections/) for more details.
+A: Absolutely! CrewAI supports various language models, including local ones. Tools like Ollama and LM Studio allow seamless integration, and AI/ML API provides access to 300+ models from various providers. Check the [LLM Connections documentation](https://docs.crewai.com/how-to/LLM-Connections/) for more details.
 
 ### Q: What makes Crews different from Flows?
 

docs/aiml_api_integration.md

@@ -0,0 +1,207 @@
+# AI/ML API Integration with CrewAI
+
+CrewAI now supports AI/ML API as a provider, giving you access to 300+ AI models through their platform. AI/ML API provides a unified interface to models from various providers including Meta (Llama), Anthropic (Claude), Mistral, Qwen, and more.
+
+## Setup
+
+1. Get your API key from [AI/ML API](https://aimlapi.com)
+2. Set your API key as an environment variable:
+
+```bash
+export AIML_API_KEY="your-api-key-here"
+```
+
+## Usage
+
+AI/ML API models use the `openai/` prefix for compatibility with LiteLLM. Here are some examples:
+
+### Basic Usage
+
+```python
+from crewai import Agent, LLM
+
+# Use Llama 3.1 70B through AI/ML API
+llm = LLM(
+    model="openai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
+    api_key="your-aiml-api-key"  # or set AIML_API_KEY env var
+)
+
+agent = Agent(
+    role="Research Assistant",
+    goal="Help with research tasks",
+    backstory="You are an expert researcher with access to advanced AI capabilities",
+    llm=llm
+)
+```
+
+### Available Models
+
+Popular models available through AI/ML API:
+
+#### Llama Models
+- `openai/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo` - Largest Llama model
+- `openai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo` - High performance
+- `openai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo` - Fast and efficient
+- `openai/meta-llama/Meta-Llama-3.2-90B-Vision-Instruct-Turbo` - Vision capabilities
+
+#### Claude Models
+- `openai/anthropic/claude-3-5-sonnet-20241022` - Latest Claude Sonnet
+- `openai/anthropic/claude-3-5-haiku-20241022` - Fast Claude model
+- `openai/anthropic/claude-3-opus-20240229` - Most capable Claude
+
+#### Other Models
+- `openai/mistralai/Mixtral-8x7B-Instruct-v0.1` - Mistral's mixture of experts
+- `openai/Qwen/Qwen2.5-72B-Instruct-Turbo` - Qwen's large model
+- `openai/deepseek-ai/DeepSeek-V2.5` - DeepSeek's latest model
+
+### Complete Example
+
+```python
+from crewai import Agent, Task, Crew, LLM
+
+# Configure AI/ML API LLM
+llm = LLM(
+    model="openai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
+    api_key="your-aiml-api-key"
+)
+
+# Create an agent with AI/ML API model
+researcher = Agent(
+    role="AI Research Specialist",
+    goal="Analyze AI trends and provide insights",
+    backstory="You are an expert in artificial intelligence with deep knowledge of current trends and developments",
+    llm=llm
+)
+
+# Create a task
+research_task = Task(
+    description="Research the latest developments in large language models and summarize key findings",
+    expected_output="A comprehensive summary of recent LLM developments with key insights",
+    agent=researcher
+)
+
+# Create and run the crew
+crew = Crew(
+    agents=[researcher],
+    tasks=[research_task]
+)
+
+result = crew.kickoff()
+print(result)
+```
+
+### Environment Configuration
+
+You can configure AI/ML API in several ways:
+
+```python
+# Method 1: Direct API key
+llm = LLM(
+    model="openai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
+    api_key="your-aiml-api-key"
+)
+
+# Method 2: Environment variable (recommended)
+# Set AIML_API_KEY in your environment
+llm = LLM(model="openai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo")
+
+# Method 3: Base URL configuration (if needed)
+llm = LLM(
+    model="openai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
+    base_url="https://api.aimlapi.com/v1",
+    api_key="your-aiml-api-key"
+)
+```
+
+## Features
+
+AI/ML API models through CrewAI support:
+
+- **Function Calling**: Most models support tool usage and function calling
+- **Streaming**: Real-time response streaming for better user experience
+- **Context Windows**: Optimized context window management for each model
+- **Vision Models**: Some models support image understanding capabilities
+- **Structured Output**: JSON and Pydantic model output formatting
+
+## Model Selection Guide
+
+Choose the right model for your use case:
+
+- **For complex reasoning**: Use Llama 3.1 405B or Claude 3.5 Sonnet
+- **For balanced performance**: Use Llama 3.1 70B or Claude 3.5 Haiku
+- **For speed and efficiency**: Use Llama 3.1 8B or smaller models
+- **For vision tasks**: Use Llama 3.2 Vision models
+- **For coding**: Consider DeepSeek or specialized coding models
+
+## Performance Considerations
+
+### Context Window Management
+
+AI/ML API models support large context windows, but be mindful of:
+
+- **Memory Usage**: Large context windows (>100K tokens) may require significant memory
+- **Processing Time**: Larger contexts take longer to process
+- **Cost Impact**: Most providers charge based on token usage
+
+### Rate Limiting Best Practices
+
+AI/ML API implements rate limiting to ensure fair usage:
+
+- **Implement Retry Logic**: Use exponential backoff for rate limit errors
+- **Monitor Usage**: Track your API usage through the AI/ML API dashboard
+- **Batch Requests**: Group multiple requests when possible to optimize throughput
+- **Cache Results**: Store frequently used responses to reduce API calls
+
+```python
+import time
+from crewai import LLM
+
+def create_llm_with_retry(model_name, max_retries=3):
+    for attempt in range(max_retries):
+        try:
+            return LLM(model=model_name)
+        except Exception as e:
+            if "rate limit" in str(e).lower() and attempt < max_retries - 1:
+                wait_time = 2 ** attempt  # Exponential backoff
+                time.sleep(wait_time)
+                continue
+            raise e
+```
+
+### Cost Optimization
+
+- **Model Selection**: Choose appropriate model size for your use case
+- **Context Management**: Trim unnecessary context to reduce token usage
+- **Streaming**: Use streaming for real-time applications to improve perceived performance
+
+## Troubleshooting
+
+### Common Issues
+
+1. **Authentication Error**: Ensure your AIML_API_KEY is set correctly
+2. **Model Not Found**: Verify the model name uses the correct `openai/` prefix
+3. **Rate Limits**: AI/ML API has rate limits; implement appropriate retry logic
+4. **Context Length**: Monitor context window usage for optimal performance
+5. **Memory Issues**: Large context windows may cause memory problems; monitor usage
+
+### Getting Help
+
+- Check the [AI/ML API Documentation](https://docs.aimlapi.com)
+- Review model-specific capabilities and limitations
+- Monitor usage and costs through the AI/ML API dashboard
+
+## Migration from Other Providers
+
+If you're migrating from other providers:
+
+```python
+# From OpenAI
+# OLD: llm = LLM(model="gpt-4")
+# NEW: llm = LLM(model="openai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo")
+
+# From Anthropic
+# OLD: llm = LLM(model="claude-3-sonnet")
+# NEW: llm = LLM(model="openai/anthropic/claude-3-5-sonnet-20241022")
+```
+
+The integration maintains full compatibility with CrewAI's existing features while providing access to AI/ML API's extensive model catalog.

docs/common-room-tracking.js

@@ -0,0 +1,18 @@
+(function() {
+  if (typeof window === 'undefined') return;
+  if (typeof window.signals !== 'undefined') return;
+  var script = document.createElement('script');
+  script.src = 'https://cdn.cr-relay.com/v1/site/883520f4-c431-44be-80e7-e123a1ee7a2b/signals.js';
+  script.async = true;
+  window.signals = Object.assign(
+    [],
+    ['page', 'identify', 'form'].reduce(function (acc, method){
+      acc[method] = function () {
+        signals.push([method, arguments]);
+        return signals;
+      };
+     return acc;
+    }, {})
+  );
+  document.head.appendChild(script);
+})(); 

docs/docs.json

@@ -85,7 +85,12 @@
           {
             "group": "MCP Integration",
             "pages": [
-              "mcp/crewai-mcp-integration"
+              "mcp/overview",
+              "mcp/stdio",
+              "mcp/sse",
+              "mcp/streamable-http",
+              "mcp/multiple-servers",
+              "mcp/security"
             ]
           },
           {
@@ -217,7 +222,6 @@
               "learn/dalle-image-generation",
               "learn/force-tool-output-as-result",
               "learn/hierarchical-process",
-              "learn/human-in-the-loop",
               "learn/human-input-on-execution",
               "learn/kickoff-async",
               "learn/kickoff-for-each",
@@ -269,6 +273,7 @@
               "enterprise/guides/slack-trigger",
               "enterprise/guides/team-management",
               "enterprise/guides/webhook-automation",
+              "enterprise/guides/human-in-the-loop",
               "enterprise/guides/zapier-trigger"
             ]
           },

docs/enterprise/guides/human-in-the-loop.mdx

@@ -0,0 +1,78 @@
+---
+title: "HITL Workflows"
+description: "Learn how to implement Human-In-The-Loop workflows in CrewAI for enhanced decision-making"
+icon: "user-check"
+---
+
+Human-In-The-Loop (HITL) is a powerful approach that combines artificial intelligence with human expertise to enhance decision-making and improve task outcomes. This guide shows you how to implement HITL within CrewAI.
+
+## Setting Up HITL Workflows
+
+<Steps>
+    <Step title="Configure Your Task">
+        Set up your task with human input enabled:
+        <Frame>
+            <img src="/images/enterprise/crew-human-input.png" alt="Crew Human Input" />
+        </Frame>
+    </Step>
+
+    <Step title="Provide Webhook URL">
+        When kicking off your crew, include a webhook URL for human input:
+        <Frame>
+            <img src="/images/enterprise/crew-webhook-url.png" alt="Crew Webhook URL" />
+        </Frame>
+    </Step>
+
+    <Step title="Receive Webhook Notification">
+        Once the crew completes the task requiring human input, you'll receive a webhook notification containing:
+            - **Execution ID**
+            - **Task ID**
+            - **Task output**
+    </Step>
+
+    <Step title="Review Task Output">
+        The system will pause in the `Pending Human Input` state. Review the task output carefully.
+    </Step>
+
+    <Step title="Submit Human Feedback">
+        Call the resume endpoint of your crew with the following information:
+        <Frame>
+            <img src="/images/enterprise/crew-resume-endpoint.png" alt="Crew Resume Endpoint" />
+        </Frame>
+        <Warning>
+            **Feedback Impact on Task Execution**:
+            It's crucial to exercise care when providing feedback, as the entire feedback content will be incorporated as additional context for further task executions.
+        </Warning>
+        This means:
+        - All information in your feedback becomes part of the task's context.
+        - Irrelevant details may negatively influence it.
+        - Concise, relevant feedback helps maintain task focus and efficiency.
+        - Always review your feedback carefully before submission to ensure it contains only pertinent information that will positively guide the task's execution.
+    </Step>
+    <Step title="Handle Negative Feedback">
+        If you provide negative feedback:
+        - The crew will retry the task with added context from your feedback.
+        - You'll receive another webhook notification for further review.
+        - Repeat steps 4-6 until satisfied.
+    </Step>
+
+    <Step title="Execution Continuation">
+        When you submit positive feedback, the execution will proceed to the next steps.
+    </Step>
+</Steps>
+
+## Best Practices
+
+- **Be Specific**: Provide clear, actionable feedback that directly addresses the task at hand
+- **Stay Relevant**: Only include information that will help improve the task execution
+- **Be Timely**: Respond to HITL prompts promptly to avoid workflow delays
+- **Review Carefully**: Double-check your feedback before submitting to ensure accuracy
+
+## Common Use Cases
+
+HITL workflows are particularly valuable for:
+- Quality assurance and validation
+- Complex decision-making scenarios
+- Sensitive or high-stakes operations
+- Creative tasks requiring human judgment
+- Compliance and regulatory reviews 

docs/installation.mdx

@@ -22,7 +22,7 @@ Watch this video tutorial for a step-by-step demonstration of the installation p
 <Note>
   **Python Version Requirements**
 
-  CrewAI requires `Python >=3.10 and <3.13`. Here's how to check your version:
+  CrewAI requires `Python >=3.10 and <=3.13`. Here's how to check your version:
   ```bash
   python3 --version
   ```

docs/learn/llm-connections.mdx

@@ -9,7 +9,7 @@ icon: brain-circuit
 CrewAI uses LiteLLM to connect to a wide variety of Language Models (LLMs). This integration provides extensive versatility, allowing you to use models from numerous providers with a simple, unified interface.
 
 <Note>
-    By default, CrewAI uses the `gpt-4o-mini` model. This is determined by the `OPENAI_MODEL_NAME` environment variable, which defaults to "gpt-4o-mini" if not set. 
+    By default, CrewAI uses the `gpt-4o-mini` model. This is determined by the `OPENAI_MODEL_NAME` environment variable, which defaults to "gpt-4o-mini" if not set.
     You can easily configure your agents to use a different model or provider as described in this guide.
 </Note>
 
@@ -117,18 +117,27 @@ You can connect to OpenAI-compatible LLMs using either environment variables or
 <Tabs>
     <Tab title="Using Environment Variables">
         <CodeGroup>
-        ```python Code
+        ```python Generic
         import os
 
         os.environ["OPENAI_API_KEY"] = "your-api-key"
         os.environ["OPENAI_API_BASE"] = "https://api.your-provider.com/v1"
         os.environ["OPENAI_MODEL_NAME"] = "your-model-name"
         ```
+
+        ```python Google
+        import os
+
+        # Example using Gemini's OpenAI-compatible API.
+        os.environ["OPENAI_API_KEY"] = "your-gemini-key"  # Should start with AIza...
+        os.environ["OPENAI_API_BASE"] = "https://generativelanguage.googleapis.com/v1beta/openai/"
+        os.environ["OPENAI_MODEL_NAME"] = "openai/gemini-2.0-flash"  # Add your Gemini model here, under openai/
+        ```
         </CodeGroup>
     </Tab>
     <Tab title="Using LLM Class Attributes">
         <CodeGroup>
-            ```python Code
+            ```python Generic
             llm = LLM(
                 model="custom-model-name",
                 api_key="your-api-key",
@@ -136,6 +145,16 @@ You can connect to OpenAI-compatible LLMs using either environment variables or
             )
             agent = Agent(llm=llm, ...)
             ```
+
+            ```python Google
+            # Example using Gemini's OpenAI-compatible API
+            llm = LLM(
+                model="openai/gemini-2.0-flash",
+                base_url="https://generativelanguage.googleapis.com/v1beta/openai/",
+                api_key="your-gemini-key",  # Should start with AIza...
+            )
+            agent = Agent(llm=llm, ...)
+            ```
         </CodeGroup>
     </Tab>
 </Tabs>
@@ -169,7 +188,7 @@ For local models like those provided by Ollama:
 
 You can change the base API URL for any LLM provider by setting the `base_url` parameter:
 
-```python Code  
+```python Code
 llm = LLM(
     model="custom-model-name",
     base_url="https://api.your-provider.com/v1",

docs/mcp/crewai-mcp-integration.mdx

@@ -1,243 +0,0 @@
----
-title: 'MCP Servers as Tools in CrewAI'
-description: 'Learn how to integrate MCP servers as tools in your CrewAI agents using the `crewai-tools` library.'
-icon: 'plug'
----
-
-## Overview
-
-The [Model Context Protocol](https://modelcontextprotocol.io/introduction) (MCP) provides a standardized way for AI agents to provide context to LLMs by communicating with external services, known as MCP Servers. 
-The `crewai-tools` library extends CrewAI's capabilities by allowing you to seamlessly integrate tools from these MCP servers into your agents. 
-This gives your crews access to a vast ecosystem of functionalities. For now, we support **Standard Input/Output** (Stdio) and **Server-Sent Events** (SSE) transport mechanisms. 
-
-<Info>
-We will also be integrating **Streamable HTTP** transport in the near future. 
-Streamable HTTP is designed for efficient, bi-directional communication over a single HTTP connection.
-</Info>
-
-## Video Tutorial
-Watch this video tutorial for a comprehensive guide on MCP integration with CrewAI:
-
-<iframe
-  width="100%"
-  height="400"
-  src="https://www.youtube.com/embed/TpQ45lAZh48"
-  title="CrewAI MCP Integration Guide"
-  frameborder="0"
-  style={{ borderRadius: '10px' }}
-  allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture"
-  allowfullscreen
-></iframe>
-
-## Installation
-
-Before you start using MCP with `crewai-tools`, you need to install the `mcp` extra `crewai-tools` dependency with the following command:
-
-```shell
-uv pip install 'crewai-tools[mcp]'
-```
-
-### Integrating MCP Tools with `MCPServerAdapter`
-
-The `MCPServerAdapter` class from `crewai-tools` is the primary way to connect to an MCP server and make its tools available to your CrewAI agents. 
-It supports different transport mechanisms, primarily **Stdio** (for local servers) and **SSE** (Server-Sent Events).You have two main options for managing the connection lifecycle:
-
-### Option 1: Fully Managed Connection (Recommended)
-
-Using a Python context manager (`with` statement) is the recommended approach. It automatically handles starting and stopping the connection to the MCP server.
-
-**For a local Stdio-based MCP server:**
-
-```python
-from crewai import Agent, Task, Crew
-from crewai_tools import MCPServerAdapter
-from mcp import StdioServerParameters
-import os
-
-server_params=StdioServerParameters(
-    command="uxv", # Or your python3 executable i.e. "python3"
-    args=["mock_server.py"],
-    env={"UV_PYTHON": "3.12", **os.environ},
-)
-
-with MCPServerAdapter(server_params) as tools:
-    print(f"Available tools from Stdio MCP server: {[tool.name for tool in tools]}")
-
-    # Example: Using the tools from the Stdio MCP server in a CrewAI Agent
-    agent = Agent(
-        role="Web Information Retriever",
-        goal="Scrape content from a specified URL.",
-        backstory="An AI that can fetch and process web page data via an MCP tool.",
-        tools=tools,
-        verbose=True,
-    )
-    task = Task(
-        description="Scrape content from a specified URL.",
-        expected_output="Scraped content from the specified URL.",
-        agent=agent,
-    )
-    crew = Crew(
-        agents=[agent],
-        tasks=[task],
-        verbose=True,
-    )
-    result = crew.kickoff()
-    print(result)
-```
-
-**For a remote SSE-based MCP server:**
-
-```python
-from crewai_tools import MCPServerAdapter
-from crewai import Agent, Task, Crew
-
-server_params = {"url": "http://localhost:8000/sse"}
-
-with MCPServerAdapter(server_params) as tools:
-    print(f"Available tools from SSE MCP server: {[tool.name for tool in tools]}")
-
-    # Example: Using the tools from the SSE MCP server in a CrewAI Agent
-    agent = Agent(
-        role="Web Information Retriever",
-        goal="Scrape content from a specified URL.",
-        backstory="An AI that can fetch and process web page data via an MCP tool.",
-        tools=tools,
-        verbose=True,
-    )
-    task = Task(
-        description="Scrape content from a specified URL.",
-        expected_output="Scraped content from the specified URL.",
-        agent=agent,
-    )
-    crew = Crew(
-        agents=[agent],
-        tasks=[task],
-        verbose=True,
-    )
-    result = crew.kickoff()
-    print(result)
-```
-
-### Option 2: More control over the MCP server connection lifecycle
-
-If you need finer-grained control over the MCP server connection lifecycle, you can instantiate `MCPServerAdapter` directly and manage its `start()` and `stop()` methods.
-
-<Info>
-You **MUST** call `mcp_server_adapter.stop()` to ensure the connection is closed and resources are released. Using a `try...finally` block is highly recommended.
-</Info>
-
-#### Stdio Transport Example (Manual)
-
-```python
-from mcp import StdioServerParameters
-from crewai_tools import MCPServerAdapter
-from crewai import Agent, Task, Crew
-import os
-
-stdio_params = StdioServerParameters(
-    command="uvx", # Or your python3 executable i.e. "python3"
-    args=["--quiet", "your-mcp-server@0.1.3"],
-    env={"UV_PYTHON": "3.12", **os.environ},
-)
-
-mcp_server_adapter = MCPServerAdapter(server_params=stdio_params)
-try:
-    mcp_server_adapter.start() # Manually start the connection
-    tools = mcp_server_adapter.tools
-    print(f"Available tools (manual Stdio): {[tool.name for tool in tools]}")
-
-    # Use 'tools' with your Agent, Task, Crew setup as in Option 1
-    agent = Agent(
-        role="Medical Researcher", 
-        goal="Find recent studies on a given topic using PubMed.", 
-        backstory="An AI assistant specialized in biomedical literature research.", 
-        tools=tools,
-        verbose=True 
-    )
-    
-    task = Task(
-        description="Search for recent articles on 'crispr gene editing'.",
-        expected_output="A summary of the top 3 recent articles.",
-        agent=agent
-    )
-    
-    crew = Crew(
-        agents=[agent],
-        tasks=[task],
-        verbose=True,
-        process=Process.sequential
-    )
-    
-    result = crew.kickoff()
-    print(result)
-finally:
-    print("Stopping Stdio MCP server connection (manual)...")
-    mcp_server_adapter.stop() # **Crucial: Ensure stop is called**
-```
-
-
-#### SSE Transport Example (Manual)
-
-```python
-from crewai_tools import MCPServerAdapter
-from crewai import Agent, Task, Crew, Process
-from mcp import StdioServerParameters
-
-
-server_params = {"url": "http://localhost:8000/sse"}
-
-try:
-    mcp_server_adapter = MCPServerAdapter(server_params)
-    mcp_server_adapter.start()
-    tools = mcp_server_adapter.tools
-    print(f"Available tools (manual SSE): {[tool.name for tool in tools]}")
-
-    agent = Agent(
-        role="Medical Researcher", 
-        goal="Find recent studies on a given topic using PubMed.", 
-        backstory="An AI assistant specialized in biomedical literature research.", 
-        tools=tools,
-        verbose=True 
-    )
-    
-    task = Task(
-        description="Search for recent articles on 'crispr gene editing'.",
-        expected_output="A summary of the top 3 recent articles.",
-        agent=agent
-    )
-    
-    crew = Crew(
-        agents=[agent],
-        tasks=[task],
-        verbose=True,
-        process=Process.sequential
-    )
-    
-    result = crew.kickoff()
-    print(result)
-finally:
-    print("Stopping SSE MCP server connection (manual)...")
-    mcp_server_adapter.stop() # **Crucial: Ensure stop is called**
-```
-
-## Staying Safe with MCP
-<Warning>
-Always ensure that you trust an MCP Server before using it.
-</Warning>
-
-#### Security Warning: DNS Rebinding Attacks
-SSE transports can be vulnerable to DNS rebinding attacks if not properly secured. 
-To prevent this:
-
-1. **Always validate Origin headers** on incoming SSE connections to ensure they come from expected sources
-2. **Avoid binding servers to all network interfaces** (0.0.0.0) when running locally - bind only to localhost (127.0.0.1) instead
-3. **Implement proper authentication** for all SSE connections
-
-Without these protections, attackers could use DNS rebinding to interact with local MCP servers from remote websites.
-
-For more details, see the [MCP Transport Security](https://modelcontextprotocol.io/docs/concepts/transports#security-considerations) documentation.
-
-### Limitations
-*   **Supported Primitives**: Currently, `MCPServerAdapter` primarily supports adapting MCP `tools`. 
-Other MCP primitives like `prompts` or `resources` are not directly integrated as CrewAI components through this adapter at this time.
-*   **Output Handling**: The adapter typically processes the primary text output from an MCP tool (e.g., `.content[0].text`). Complex or multi-modal outputs might require custom handling if not fitting this pattern.

docs/mcp/multiple-servers.mdx

@@ -0,0 +1,64 @@
+---
+title: Connecting to Multiple MCP Servers
+description: Learn how to use MCPServerAdapter in CrewAI to connect to multiple MCP servers simultaneously and aggregate their tools.
+icon: layer-group
+---
+
+## Overview
+
+`MCPServerAdapter` in `crewai-tools` allows you to connect to multiple MCP servers concurrently. This is useful when your agents need to access tools distributed across different services or environments. The adapter aggregates tools from all specified servers, making them available to your CrewAI agents.
+
+## Configuration
+
+To connect to multiple servers, you provide a list of server parameter dictionaries to `MCPServerAdapter`. Each dictionary in the list should define the parameters for one MCP server.
+
+Supported transport types for each server in the list include `stdio`, `sse`, and `streamable-http`.
+
+```python
+from crewai import Agent, Task, Crew, Process
+from crewai_tools import MCPServerAdapter
+from mcp import StdioServerParameters # Needed for Stdio example
+
+# Define parameters for multiple MCP servers
+server_params_list = [
+    # Streamable HTTP Server
+    {
+        "url": "http://localhost:8001/mcp", 
+        "transport": "streamable-http"
+    },
+    # SSE Server
+    {
+        "url": "http://localhost:8000/sse",
+        "transport": "sse"
+    },
+    # StdIO Server
+    StdioServerParameters(
+        command="python3",
+        args=["servers/your_stdio_server.py"],
+        env={"UV_PYTHON": "3.12", **os.environ},
+    )
+]
+
+try:
+    with MCPServerAdapter(server_params_list) as aggregated_tools:
+        print(f"Available aggregated tools: {[tool.name for tool in aggregated_tools]}")
+
+        multi_server_agent = Agent(
+            role="Versatile Assistant",
+            goal="Utilize tools from local Stdio, remote SSE, and remote HTTP MCP servers.",
+            backstory="An AI agent capable of leveraging a diverse set of tools from multiple sources.",
+            tools=aggregated_tools, # All tools are available here
+            verbose=True,
+        )
+
+        ... # Your other agent, tasks, and crew code here
+
+except Exception as e:
+    print(f"Error connecting to or using multiple MCP servers (Managed): {e}")
+    print("Ensure all MCP servers are running and accessible with correct configurations.")
+
+```
+
+## Connection Management
+
+When using the context manager (`with` statement), `MCPServerAdapter` handles the lifecycle (start and stop) of all connections to the configured MCP servers. This simplifies resource management and ensures that all connections are properly closed when the context is exited.

docs/mcp/overview.mdx

@@ -0,0 +1,164 @@
+---
+title: 'MCP Servers as Tools in CrewAI'
+description: 'Learn how to integrate MCP servers as tools in your CrewAI agents using the `crewai-tools` library.'
+icon: plug
+---
+
+## Overview
+
+The [Model Context Protocol](https://modelcontextprotocol.io/introduction) (MCP) provides a standardized way for AI agents to provide context to LLMs by communicating with external services, known as MCP Servers. 
+The `crewai-tools` library extends CrewAI's capabilities by allowing you to seamlessly integrate tools from these MCP servers into your agents. 
+This gives your crews access to a vast ecosystem of functionalities. 
+
+We currently support the following transport mechanisms: 
+
+- **Stdio**: for local servers (communication via standard input/output between processes on the same machine)
+- **Server-Sent Events (SSE)**: for remote servers (unidirectional, real-time data streaming from server to client over HTTP)
+- **Streamable HTTP**: for remote servers (flexible, potentially bi-directional communication over HTTP, often utilizing SSE for server-to-client streams)
+
+## Video Tutorial
+Watch this video tutorial for a comprehensive guide on MCP integration with CrewAI:
+
+<iframe
+  width="100%"
+  height="400"
+  src="https://www.youtube.com/embed/TpQ45lAZh48"
+  title="CrewAI MCP Integration Guide"
+  frameborder="0"
+  style={{ borderRadius: '10px' }}
+  allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture"
+  allowfullscreen
+></iframe>
+
+## Installation
+
+Before you start using MCP with `crewai-tools`, you need to install the `mcp` extra `crewai-tools` dependency with the following command:
+
+```shell
+uv pip install 'crewai-tools[mcp]'
+```
+
+## Key Concepts & Getting Started
+
+The `MCPServerAdapter` class from `crewai-tools` is the primary way to connect to an MCP server and make its tools available to your CrewAI agents. It supports different transport mechanisms and simplifies connection management.
+
+Using a Python context manager (`with` statement) is the **recommended approach** for `MCPServerAdapter`. It automatically handles starting and stopping the connection to the MCP server.
+
+```python
+from crewai import Agent
+from crewai_tools import MCPServerAdapter
+from mcp import StdioServerParameters # For Stdio Server
+
+# Example server_params (choose one based on your server type):
+# 1. Stdio Server:
+server_params=StdioServerParameters(
+    command="python3", 
+    args=["servers/your_server.py"],
+    env={"UV_PYTHON": "3.12", **os.environ},
+)
+
+# 2. SSE Server:
+server_params = {
+    "url": "http://localhost:8000/sse", 
+    "transport": "sse"
+}
+
+# 3. Streamable HTTP Server:
+server_params = {
+    "url": "http://localhost:8001/mcp", 
+    "transport": "streamable-http"
+}
+
+# Example usage (uncomment and adapt once server_params is set):
+with MCPServerAdapter(server_params) as mcp_tools:
+    print(f"Available tools: {[tool.name for tool in mcp_tools]}")
+    
+    my_agent = Agent(
+        role="MCP Tool User",
+        goal="Utilize tools from an MCP server.",
+        backstory="I can connect to MCP servers and use their tools.",
+        tools=mcp_tools, # Pass the loaded tools to your agent
+        reasoning=True,
+        verbose=True
+    )
+    # ... rest of your crew setup ...
+```
+This general pattern shows how to integrate tools. For specific examples tailored to each transport, refer to the detailed guides below.
+
+## Explore MCP Integrations
+
+<CardGroup cols={2}>
+  <Card 
+    title="Stdio Transport" 
+    icon="server" 
+    href="/mcp/stdio"
+    color="#3B82F6"
+  >
+    Connect to local MCP servers via standard input/output. Ideal for scripts and local executables.
+  </Card>
+  <Card 
+    title="SSE Transport" 
+    icon="wifi" 
+    href="/mcp/sse"
+    color="#10B981"
+  >
+    Integrate with remote MCP servers using Server-Sent Events for real-time data streaming.
+  </Card>
+  <Card 
+    title="Streamable HTTP Transport" 
+    icon="globe" 
+    href="/mcp/streamable-http"
+    color="#F59E0B"
+  >
+    Utilize flexible Streamable HTTP for robust communication with remote MCP servers.
+  </Card>
+  <Card 
+    title="Connecting to Multiple Servers" 
+    icon="layer-group" 
+    href="/mcp/multiple-servers"
+    color="#8B5CF6"
+  >
+    Aggregate tools from several MCP servers simultaneously using a single adapter.
+  </Card>
+  <Card 
+    title="Security Considerations" 
+    icon="lock" 
+    href="/mcp/security"
+    color="#EF4444"
+  >
+    Review important security best practices for MCP integration to keep your agents safe.
+  </Card>
+</CardGroup>
+
+Checkout this repository for full demos and examples of MCP integration with CrewAI! 👇
+
+<Card 
+title="GitHub Repository"
+icon="github"
+href="https://github.com/tonykipkemboi/crewai-mcp-demo"
+target="_blank"
+>
+CrewAI MCP Demo
+</Card>
+
+## Staying Safe with MCP
+<Warning>
+Always ensure that you trust an MCP Server before using it.
+</Warning>
+
+#### Security Warning: DNS Rebinding Attacks
+SSE transports can be vulnerable to DNS rebinding attacks if not properly secured. 
+To prevent this:
+
+1. **Always validate Origin headers** on incoming SSE connections to ensure they come from expected sources
+2. **Avoid binding servers to all network interfaces** (0.0.0.0) when running locally - bind only to localhost (127.0.0.1) instead
+3. **Implement proper authentication** for all SSE connections
+
+Without these protections, attackers could use DNS rebinding to interact with local MCP servers from remote websites.
+
+For more details, see the [Anthropic's MCP Transport Security docs](https://modelcontextprotocol.io/docs/concepts/transports#security-considerations).
+
+### Limitations
+*   **Supported Primitives**: Currently, `MCPServerAdapter` primarily supports adapting MCP `tools`. 
+Other MCP primitives like `prompts` or `resources` are not directly integrated as CrewAI components through this adapter at this time.
+*   **Output Handling**: The adapter typically processes the primary text output from an MCP tool (e.g., `.content[0].text`). Complex or multi-modal outputs might require custom handling if not fitting this pattern.

docs/mcp/security.mdx

@@ -0,0 +1,166 @@
+---
+title: MCP Security Considerations
+description: Learn about important security best practices when integrating MCP servers with your CrewAI agents.
+icon: lock
+---
+
+## Overview
+
+<Warning>
+The most critical aspect of MCP security is **trust**. You should **only** connect your CrewAI agents to MCP servers that you fully trust.
+</Warning>
+
+When integrating external services like MCP (Model Context Protocol) servers into your CrewAI agents, security is paramount. 
+MCP servers can execute code, access data, or interact with other systems based on the tools they expose. 
+It's crucial to understand the implications and follow best practices to protect your applications and data.
+
+### Risks
+
+- Execute arbitrary code on the machine where the agent is running (especially with `Stdio` transport if the server can control the command executed).
+- Expose sensitive data from your agent or its environment.
+- Manipulate your agent's behavior in unintended ways, including making unauthorized API calls on your behalf.
+- Hijack your agent's reasoning process through sophisticated prompt injection techniques (see below).
+
+### 1. Trusting MCP Servers
+
+<Warning>
+**Only connect to MCP servers that you trust.**
+</Warning>
+
+Before configuring `MCPServerAdapter` to connect to an MCP server, ensure you know:
+- **Who operates the server?** Is it a known, reputable service, or an internal server under your control?
+- **What tools does it expose?** Understand the capabilities of the tools. Could they be misused if an attacker gained control or if the server itself is malicious?
+- **What data does it access or process?** Be aware of any sensitive information that might be sent to or handled by the MCP server.
+
+Avoid connecting to unknown or unverified MCP servers, especially if your agents handle sensitive tasks or data.
+
+### 2. Secure Prompt Injection via Tool Metadata: The "Model Control Protocol" Risk
+
+A significant and subtle risk is the potential for prompt injection through tool metadata. Here's how it works:
+
+1.  When your CrewAI agent connects to an MCP server, it typically requests a list of available tools.
+2.  The MCP server responds with metadata for each tool, including its name, description, and parameter descriptions.
+3.  Your agent's underlying Language Model (LLM) uses this metadata to understand how and when to use the tools. This metadata is often incorporated into the LLM's system prompt or context.
+4.  A malicious MCP server can craft its tool metadata (names, descriptions) to include hidden or overt instructions. These instructions can act as a prompt injection, effectively telling your LLM to behave in a certain way, reveal sensitive information, or perform malicious actions.
+
+**Crucially, this attack can occur simply by connecting to a malicious server and listing its tools, even if your agent never explicitly decides to *use* any of those tools.** The mere exposure to the malicious metadata can be enough to compromise the agent's behavior.
+
+**Mitigation:**
+
+*   **Extreme Caution with Untrusted Servers:** Reiterate: *Do not connect to MCP servers you do not fully trust.* The risk of metadata injection makes this paramount.
+
+### Stdio Transport Security
+
+Stdio (Standard Input/Output) transport is typically used for local MCP servers running on the same machine as your CrewAI application.
+
+- **Process Isolation**: While generally safer as it doesn't involve network exposure by default, ensure the script or command run by `StdioServerParameters` is from a trusted source and has appropriate file system permissions. A malicious Stdio server script could still harm your local system.
+- **Input Sanitization**: If your Stdio server script takes complex inputs derived from agent interactions, ensure the script itself sanitizes these inputs to prevent command injection or other vulnerabilities within the script's logic.
+- **Resource Limits**: Be mindful that a local Stdio server process consumes local resources (CPU, memory). Ensure it's well-behaved and won't exhaust system resources.
+
+### Confused Deputy Attacks
+
+The [Confused Deputy Problem](https://en.wikipedia.org/wiki/Confused_deputy_problem) is a classic security vulnerability that can manifest in MCP integrations, especially when an MCP server acts as a proxy to other third-party services (e.g., Google Calendar, GitHub) that use OAuth 2.0 for authorization.
+
+**Scenario:**
+
+1.  An MCP server (let's call it `MCP-Proxy`) allows your agent to interact with `ThirdPartyAPI`.
+2.  `MCP-Proxy` uses its own single, static `client_id` when talking to `ThirdPartyAPI`'s authorization server.
+3.  You, as the user, legitimately authorize `MCP-Proxy` to access `ThirdPartyAPI` on your behalf. During this, `ThirdPartyAPI`'s auth server might set a cookie in your browser indicating your consent for `MCP-Proxy`'s `client_id`.
+4.  An attacker crafts a malicious link. This link initiates an OAuth flow with `MCP-Proxy`, but is designed to trick `ThirdPartyAPI`'s auth server.
+5.  If you click this link, and `ThirdPartyAPI`'s auth server sees your existing consent cookie for `MCP-Proxy`'s `client_id`, it might *skip* asking for your consent again.
+6.  `MCP-Proxy` might then be tricked into forwarding an authorization code (for `ThirdPartyAPI`) to the attacker, or an MCP authorization code that the attacker can use to impersonate you to `MCP-Proxy`.
+
+**Mitigation (Primarily for MCP Server Developers):**
+
+*   MCP proxy servers using static client IDs for downstream services **must** obtain explicit user consent for *each client application or agent* connecting to them *before* initiating an OAuth flow with the third-party service. This means `MCP-Proxy` itself should show a consent screen.
+
+**CrewAI User Implication:**
+
+*   Be cautious if an MCP server redirects you for multiple OAuth authentications, especially if it seems unexpected or if the permissions requested are overly broad.
+*   Prefer MCP servers that clearly delineate their own identity versus the third-party services they might proxy.
+
+### Remote Transport Security (SSE & Streamable HTTP)
+
+When connecting to remote MCP servers via Server-Sent Events (SSE) or Streamable HTTP, standard web security practices are essential.
+
+### SSE Security Considerations
+
+### a. DNS Rebinding Attacks (Especially for SSE)
+
+<Critical>
+**Protect against DNS Rebinding Attacks.**
+</Critical>
+
+DNS rebinding allows an attacker-controlled website to bypass the same-origin policy and make requests to servers on the user's local network (e.g., `localhost`) or intranet. This is particularly risky if you run an MCP server locally (e.g., for development) and an agent in a browser-like environment (though less common for typical CrewAI backend setups) or if the MCP server is on an internal network.
+
+**Mitigation Strategies for MCP Server Implementers:**
+- **Validate `Origin` and `Host` Headers**: MCP servers (especially SSE ones) should validate the `Origin` and/or `Host` HTTP headers to ensure requests are coming from expected domains/clients.
+- **Bind to `localhost` (127.0.0.1)**: When running MCP servers locally for development, bind them to `127.0.0.1` instead of `0.0.0.0`. This prevents them from being accessible from other machines on the network.
+- **Authentication**: Require authentication for all connections to your MCP server if it's not intended for public anonymous access.
+
+### b. Use HTTPS
+
+- **Encrypt Data in Transit**: Always use HTTPS (HTTP Secure) for the URLs of remote MCP servers. This encrypts the communication between your CrewAI application and the MCP server, protecting against eavesdropping and man-in-the-middle attacks. `MCPServerAdapter` will respect the scheme (`http` or `https`) provided in the URL.
+
+### c. Token Passthrough (Anti-Pattern)
+
+This is primarily a concern for MCP server developers but understanding it helps in choosing secure servers.
+
+"Token passthrough" is when an MCP server accepts an access token from your CrewAI agent (which might be a token for a *different* service, say `ServiceA`) and simply passes it through to another downstream API (`ServiceB`) without proper validation. Specifically, `ServiceB` (or the MCP server itself) should only accept tokens that were explicitly issued *for them* (i.e., the 'audience' claim in the token matches the server/service).
+
+**Risks:**
+
+*   Bypasses security controls (like rate limiting or fine-grained permissions) on the MCP server or the downstream API.
+*   Breaks audit trails and accountability.
+*   Allows misuse of stolen tokens.
+
+**Mitigation (For MCP Server Developers):**
+
+*   MCP servers **MUST NOT** accept tokens that were not explicitly issued for them. They must validate the token's audience claim.
+
+**CrewAI User Implication:**
+
+*   While not directly controllable by the user, this highlights the importance of connecting to well-designed MCP servers that adhere to security best practices.
+
+#### Authentication and Authorization
+
+- **Verify Identity**: If the MCP server provides sensitive tools or access to private data, it MUST implement strong authentication mechanisms to verify the identity of the client (your CrewAI application). This could involve API keys, OAuth tokens, or other standard methods.
+- **Principle of Least Privilege**: Ensure the credentials used by `MCPServerAdapter` (if any) have only the necessary permissions to access the required tools.
+
+### d. Input Validation and Sanitization
+
+- **Input Validation is Critical**: MCP servers **must** rigorously validate all inputs received from agents *before* processing them or passing them to tools. This is a primary defense against many common vulnerabilities:
+    - **Command Injection:** If a tool constructs shell commands, SQL queries, or other interpreted language statements based on input, the server must meticulously sanitize this input to prevent malicious commands from being injected and executed.
+    - **Path Traversal:** If a tool accesses files based on input parameters, the server must validate and sanitize these paths to prevent access to unauthorized files or directories (e.g., by blocking `../` sequences).
+    - **Data Type & Range Checks:** Servers must ensure that input data conforms to the expected data types (e.g., string, number, boolean) and falls within acceptable ranges or adheres to defined formats (e.g., regex for URLs).
+    - **JSON Schema Validation:** All tool parameters should be strictly validated against their defined JSON schema. This helps catch malformed requests early.
+- **Client-Side Awareness**: While server-side validation is paramount, as a CrewAI user, be mindful of the data your agents are constructed to send to MCP tools, especially if interacting with less-trusted or new MCP servers.
+
+### e. Rate Limiting and Resource Management
+
+- **Prevent Abuse**: MCP servers should implement rate limiting to prevent abuse, whether intentional (Denial of Service attacks) or unintentional (e.g., a misconfigured agent making too many requests).
+- **Client-Side Retries**: Implement sensible retry logic in your CrewAI tasks if transient network issues or server rate limits are expected, but avoid aggressive retries that could exacerbate server load.
+
+## 4. Secure MCP Server Implementation Advice (For Developers)
+
+If you are developing an MCP server that CrewAI agents might connect to, consider these best practices in addition to the points above:
+
+- **Follow Secure Coding Practices**: Adhere to standard secure coding principles for your chosen language and framework (e.g., OWASP Top 10).
+- **Principle of Least Privilege**: Ensure the process running the MCP server (especially for `Stdio`) has only the minimum necessary permissions. Tools themselves should also operate with the least privilege required to perform their function.
+- **Dependency Management**: Keep all server-side dependencies, including operating system packages, language runtimes, and third-party libraries, up-to-date to patch known vulnerabilities. Use tools to scan for vulnerable dependencies.
+- **Secure Defaults**: Design your server and its tools to be secure by default. For example, features that could be risky should be off by default or require explicit opt-in with clear warnings.
+- **Access Control for Tools**: Implement robust mechanisms to control which authenticated and authorized agents or users can access specific tools, especially those that are powerful, sensitive, or incur costs.
+- **Secure Error Handling**: Servers should not expose detailed internal error messages, stack traces, or debugging information to the client, as these can reveal internal workings or potential vulnerabilities. Log errors comprehensively on the server-side for diagnostics.
+- **Comprehensive Logging and Monitoring**: Implement detailed logging of security-relevant events (e.g., authentication attempts, tool invocations, errors, authorization changes). Monitor these logs for suspicious activity or abuse patterns.
+- **Adherence to MCP Authorization Spec**: If implementing authentication and authorization, strictly follow the [MCP Authorization specification](https://modelcontextprotocol.io/specification/draft/basic/authorization) and relevant [OAuth 2.0 security best practices](https://datatracker.ietf.org/doc/html/rfc9700).
+- **Regular Security Audits**: If your MCP server handles sensitive data, performs critical operations, or is publicly exposed, consider periodic security audits by qualified professionals.
+
+## 5. Further Reading
+
+For more detailed information on MCP security, refer to the official documentation:
+- **[MCP Transport Security](https://modelcontextprotocol.io/docs/concepts/transports#security-considerations)**
+
+By understanding these security considerations and implementing best practices, you can safely leverage the power of MCP servers in your CrewAI projects. 
+These are by no means exhaustive, but they cover the most common and critical security concerns. 
+The threats will continue to evolve, so it's important to stay informed and adapt your security measures accordingly.
+

docs/mcp/sse.mdx

@@ -0,0 +1,150 @@
+---
+title: SSE Transport
+description: Learn how to connect CrewAI to remote MCP servers using Server-Sent Events (SSE) for real-time communication.
+icon: wifi
+---
+
+## Overview
+
+Server-Sent Events (SSE) provide a standard way for a web server to send updates to a client over a single, long-lived HTTP connection. In the context of MCP, SSE is used for remote servers to stream data (like tool responses) to your CrewAI application in real-time.
+
+## Key Concepts
+
+- **Remote Servers**: SSE is suitable for MCP servers hosted remotely.
+- **Unidirectional Stream**: Typically, SSE is a one-way communication channel from server to client.
+- **`MCPServerAdapter` Configuration**: For SSE, you'll provide the server's URL and specify the transport type.
+
+## Connecting via SSE
+
+You can connect to an SSE-based MCP server using two main approaches for managing the connection lifecycle:
+
+### 1. Fully Managed Connection (Recommended)
+
+Using a Python context manager (`with` statement) is the recommended approach. It automatically handles establishing and closing the connection to the SSE MCP server.
+
+```python
+from crewai import Agent, Task, Crew, Process
+from crewai_tools import MCPServerAdapter
+
+server_params = {
+    "url": "http://localhost:8000/sse", # Replace with your actual SSE server URL
+    "transport": "sse" 
+}
+
+# Using MCPServerAdapter with a context manager
+try:
+    with MCPServerAdapter(server_params) as tools:
+        print(f"Available tools from SSE MCP server: {[tool.name for tool in tools]}")
+
+        # Example: Using a tool from the SSE MCP server
+        sse_agent = Agent(
+            role="Remote Service User",
+            goal="Utilize a tool provided by a remote SSE MCP server.",
+            backstory="An AI agent that connects to external services via SSE.",
+            tools=tools,
+            reasoning=True,
+            verbose=True,
+        )
+
+        sse_task = Task(
+            description="Fetch real-time stock updates for 'AAPL' using an SSE tool.",
+            expected_output="The latest stock price for AAPL.",
+            agent=sse_agent,
+            markdown=True
+        )
+
+        sse_crew = Crew(
+            agents=[sse_agent],
+            tasks=[sse_task],
+            verbose=True,
+            process=Process.sequential
+        )
+        
+        if tools: # Only kickoff if tools were loaded
+            result = sse_crew.kickoff() # Add inputs={'stock_symbol': 'AAPL'} if tool requires it
+            print("\nCrew Task Result (SSE - Managed):\n", result)
+        else:
+            print("Skipping crew kickoff as tools were not loaded (check server connection).")
+
+except Exception as e:
+    print(f"Error connecting to or using SSE MCP server (Managed): {e}")
+    print("Ensure the SSE MCP server is running and accessible at the specified URL.")
+
+```
+
+<Note>
+Replace `"http://localhost:8000/sse"` with the actual URL of your SSE MCP server.
+</Note>
+
+### 2. Manual Connection Lifecycle
+
+If you need finer-grained control, you can manage the `MCPServerAdapter` connection lifecycle manually.
+
+<Info>
+You **MUST** call `mcp_server_adapter.stop()` to ensure the connection is closed and resources are released. Using a `try...finally` block is highly recommended.
+</Info>
+
+```python
+from crewai import Agent, Task, Crew, Process
+from crewai_tools import MCPServerAdapter
+
+server_params = {
+    "url": "http://localhost:8000/sse", # Replace with your actual SSE server URL
+    "transport": "sse"
+}
+
+mcp_server_adapter = None 
+try:
+    mcp_server_adapter = MCPServerAdapter(server_params)
+    mcp_server_adapter.start()
+    tools = mcp_server_adapter.tools
+    print(f"Available tools (manual SSE): {[tool.name for tool in tools]}")
+
+    manual_sse_agent = Agent(
+        role="Remote Data Analyst",
+        goal="Analyze data fetched from a remote SSE MCP server using manual connection management.",
+        backstory="An AI skilled in handling SSE connections explicitly.",
+        tools=tools,
+        verbose=True
+    )
+    
+    analysis_task = Task(
+        description="Fetch and analyze the latest user activity trends from the SSE server.",
+        expected_output="A summary report of user activity trends.",
+        agent=manual_sse_agent
+    )
+    
+    analysis_crew = Crew(
+        agents=[manual_sse_agent],
+        tasks=[analysis_task],
+        verbose=True,
+        process=Process.sequential
+    )
+    
+    result = analysis_crew.kickoff()
+    print("\nCrew Task Result (SSE - Manual):\n", result)
+
+except Exception as e:
+    print(f"An error occurred during manual SSE MCP integration: {e}")
+    print("Ensure the SSE MCP server is running and accessible.")
+finally:
+    if mcp_server_adapter and mcp_server_adapter.is_connected:
+        print("Stopping SSE MCP server connection (manual)...")
+        mcp_server_adapter.stop()  # **Crucial: Ensure stop is called**
+    elif mcp_server_adapter:
+        print("SSE MCP server adapter was not connected. No stop needed or start failed.")
+
+```
+
+## Security Considerations for SSE
+
+<Warning>
+**DNS Rebinding Attacks**: SSE transports can be vulnerable to DNS rebinding attacks if the MCP server is not properly secured. This could allow malicious websites to interact with local or intranet-based MCP servers.
+</Warning>
+
+To mitigate this risk:
+- MCP server implementations should **validate `Origin` headers** on incoming SSE connections.
+- When running local SSE MCP servers for development, **bind only to `localhost` (`127.0.0.1`)** rather than all network interfaces (`0.0.0.0`).
+- Implement **proper authentication** for all SSE connections if they expose sensitive tools or data.
+
+For a comprehensive overview of security best practices, please refer to our [Security Considerations](./security.mdx) page and the official [MCP Transport Security documentation](https://modelcontextprotocol.io/docs/concepts/transports#security-considerations).

docs/mcp/stdio.mdx

@@ -0,0 +1,134 @@
+---
+title: Stdio Transport
+description: Learn how to connect CrewAI to local MCP servers using the Stdio (Standard Input/Output) transport mechanism.
+icon: server
+---
+
+## Overview
+
+The Stdio (Standard Input/Output) transport is designed for connecting `MCPServerAdapter` to local MCP servers that communicate over their standard input and output streams. This is typically used when the MCP server is a script or executable running on the same machine as your CrewAI application.
+
+## Key Concepts
+
+- **Local Execution**: Stdio transport manages a locally running process for the MCP server.
+- **`StdioServerParameters`**: This class from the `mcp` library is used to configure the command, arguments, and environment variables for launching the Stdio server.
+
+## Connecting via Stdio
+
+You can connect to an Stdio-based MCP server using two main approaches for managing the connection lifecycle:
+
+### 1. Fully Managed Connection (Recommended)
+
+Using a Python context manager (`with` statement) is the recommended approach. It automatically handles starting the MCP server process and stopping it when the context is exited.
+
+```python
+from crewai import Agent, Task, Crew, Process
+from crewai_tools import MCPServerAdapter
+from mcp import StdioServerParameters
+import os
+
+# Create a StdioServerParameters object
+server_params=StdioServerParameters(
+    command="python3", 
+    args=["servers/your_stdio_server.py"],
+    env={"UV_PYTHON": "3.12", **os.environ},
+)
+
+with MCPServerAdapter(server_params) as tools:
+    print(f"Available tools from Stdio MCP server: {[tool.name for tool in tools]}")
+
+    # Example: Using the tools from the Stdio MCP server in a CrewAI Agent
+    research_agent = Agent(
+        role="Local Data Processor",
+        goal="Process data using a local Stdio-based tool.",
+        backstory="An AI that leverages local scripts via MCP for specialized tasks.",
+        tools=tools,
+        reasoning=True,
+        verbose=True,
+    )
+    
+    processing_task = Task(
+        description="Process the input data file 'data.txt' and summarize its contents.",
+        expected_output="A summary of the processed data.",
+        agent=research_agent,
+        markdown=True
+    )
+    
+    data_crew = Crew(
+        agents=[research_agent],
+        tasks=[processing_task],
+        verbose=True,
+        process=Process.sequential 
+    )
+   
+    result = data_crew.kickoff()
+    print("\nCrew Task Result (Stdio - Managed):\n", result)
+
+```
+
+### 2. Manual Connection Lifecycle
+
+If you need finer-grained control over when the Stdio MCP server process is started and stopped, you can manage the `MCPServerAdapter` lifecycle manually.
+
+<Info>
+You **MUST** call `mcp_server_adapter.stop()` to ensure the server process is terminated and resources are released. Using a `try...finally` block is highly recommended.
+</Info>
+
+```python
+from crewai import Agent, Task, Crew, Process
+from crewai_tools import MCPServerAdapter
+from mcp import StdioServerParameters
+import os
+
+# Create a StdioServerParameters object
+stdio_params=StdioServerParameters(
+    command="python3", 
+    args=["servers/your_stdio_server.py"],
+    env={"UV_PYTHON": "3.12", **os.environ},
+)
+
+mcp_server_adapter = MCPServerAdapter(server_params=stdio_params)
+try:
+    mcp_server_adapter.start()  # Manually start the connection and server process
+    tools = mcp_server_adapter.tools
+    print(f"Available tools (manual Stdio): {[tool.name for tool in tools]}")
+
+    # Example: Using the tools with your Agent, Task, Crew setup
+    manual_agent = Agent(
+        role="Local Task Executor",
+        goal="Execute a specific local task using a manually managed Stdio tool.",
+        backstory="An AI proficient in controlling local processes via MCP.",
+        tools=tools,
+        verbose=True
+    )
+    
+    manual_task = Task(
+        description="Execute the 'perform_analysis' command via the Stdio tool.",
+        expected_output="Results of the analysis.",
+        agent=manual_agent
+    )
+    
+    manual_crew = Crew(
+        agents=[manual_agent],
+        tasks=[manual_task],
+        verbose=True,
+        process=Process.sequential
+    )
+        
+       
+    result = manual_crew.kickoff() # Actual inputs depend on your tool
+    print("\nCrew Task Result (Stdio - Manual):\n", result)
+            
+except Exception as e:
+    print(f"An error occurred during manual Stdio MCP integration: {e}")
+finally:
+    if mcp_server_adapter and mcp_server_adapter.is_connected: # Check if connected before stopping
+        print("Stopping Stdio MCP server connection (manual)...")
+        mcp_server_adapter.stop()  # **Crucial: Ensure stop is called**
+    elif mcp_server_adapter: # If adapter exists but not connected (e.g. start failed)
+        print("Stdio MCP server adapter was not connected. No stop needed or start failed.")
+
+```
+
+Remember to replace placeholder paths and commands with your actual Stdio server details. The `env` parameter in `StdioServerParameters` can 
+be used to set environment variables for the server process, which can be useful for configuring its behavior or providing necessary paths (like `PYTHONPATH`).

docs/mcp/streamable-http.mdx

@@ -0,0 +1,135 @@
+---
+title: Streamable HTTP Transport
+description: Learn how to connect CrewAI to remote MCP servers using the flexible Streamable HTTP transport.
+icon: globe
+---
+
+## Overview
+
+Streamable HTTP transport provides a flexible way to connect to remote MCP servers. It's often built upon HTTP and can support various communication patterns, including request-response and streaming, sometimes utilizing Server-Sent Events (SSE) for server-to-client streams within a broader HTTP interaction.
+
+## Key Concepts
+
+- **Remote Servers**: Designed for MCP servers hosted remotely.
+- **Flexibility**: Can support more complex interaction patterns than plain SSE, potentially including bi-directional communication if the server implements it.
+- **`MCPServerAdapter` Configuration**: You'll need to provide the server's base URL for MCP communication and specify `"streamable-http"` as the transport type.
+
+## Connecting via Streamable HTTP
+
+You have two primary methods for managing the connection lifecycle with a Streamable HTTP MCP server:
+
+### 1. Fully Managed Connection (Recommended)
+
+The recommended approach is to use a Python context manager (`with` statement), which handles the connection's setup and teardown automatically.
+
+```python
+from crewai import Agent, Task, Crew, Process
+from crewai_tools import MCPServerAdapter
+
+server_params = {
+    "url": "http://localhost:8001/mcp", # Replace with your actual Streamable HTTP server URL
+    "transport": "streamable-http"
+}
+
+try:
+    with MCPServerAdapter(server_params) as tools:
+        print(f"Available tools from Streamable HTTP MCP server: {[tool.name for tool in tools]}")
+
+        http_agent = Agent(
+            role="HTTP Service Integrator",
+            goal="Utilize tools from a remote MCP server via Streamable HTTP.",
+            backstory="An AI agent adept at interacting with complex web services.",
+            tools=tools,
+            verbose=True,
+        )
+
+        http_task = Task(
+            description="Perform a complex data query using a tool from the Streamable HTTP server.",
+            expected_output="The result of the complex data query.",
+            agent=http_agent,
+        )
+
+        http_crew = Crew(
+            agents=[http_agent],
+            tasks=[http_task],
+            verbose=True,
+            process=Process.sequential
+        )
+        
+        result = http_crew.kickoff() 
+        print("\nCrew Task Result (Streamable HTTP - Managed):\n", result)
+
+except Exception as e:
+    print(f"Error connecting to or using Streamable HTTP MCP server (Managed): {e}")
+    print("Ensure the Streamable HTTP MCP server is running and accessible at the specified URL.")
+
+```
+**Note:** Replace `"http://localhost:8001/mcp"` with the actual URL of your Streamable HTTP MCP server.
+
+### 2. Manual Connection Lifecycle
+
+For scenarios requiring more explicit control, you can manage the `MCPServerAdapter` connection manually.
+
+<Info>
+It is **critical** to call `mcp_server_adapter.stop()` when you are done to close the connection and free up resources. A `try...finally` block is the safest way to ensure this.
+</Info>
+
+```python
+from crewai import Agent, Task, Crew, Process
+from crewai_tools import MCPServerAdapter
+
+server_params = {
+    "url": "http://localhost:8001/mcp", # Replace with your actual Streamable HTTP server URL
+    "transport": "streamable-http"
+}
+
+mcp_server_adapter = None 
+try:
+    mcp_server_adapter = MCPServerAdapter(server_params)
+    mcp_server_adapter.start()
+    tools = mcp_server_adapter.tools
+    print(f"Available tools (manual Streamable HTTP): {[tool.name for tool in tools]}")
+
+    manual_http_agent = Agent(
+        role="Advanced Web Service User",
+        goal="Interact with an MCP server using manually managed Streamable HTTP connections.",
+        backstory="An AI specialist in fine-tuning HTTP-based service integrations.",
+        tools=tools,
+        verbose=True
+    )
+    
+    data_processing_task = Task(
+        description="Submit data for processing and retrieve results via Streamable HTTP.",
+        expected_output="Processed data or confirmation.",
+        agent=manual_http_agent
+    )
+    
+    data_crew = Crew(
+        agents=[manual_http_agent],
+        tasks=[data_processing_task],
+        verbose=True,
+        process=Process.sequential
+    )
+    
+    result = data_crew.kickoff()
+    print("\nCrew Task Result (Streamable HTTP - Manual):\n", result)
+
+except Exception as e:
+    print(f"An error occurred during manual Streamable HTTP MCP integration: {e}")
+    print("Ensure the Streamable HTTP MCP server is running and accessible.")
+finally:
+    if mcp_server_adapter and mcp_server_adapter.is_connected:
+        print("Stopping Streamable HTTP MCP server connection (manual)...")
+        mcp_server_adapter.stop()  # **Crucial: Ensure stop is called**
+    elif mcp_server_adapter:
+        print("Streamable HTTP MCP server adapter was not connected. No stop needed or start failed.")
+```
+
+## Security Considerations
+
+When using Streamable HTTP transport, general web security best practices are paramount:
+- **Use HTTPS**: Always prefer HTTPS (HTTP Secure) for your MCP server URLs to encrypt data in transit.
+- **Authentication**: Implement robust authentication mechanisms if your MCP server exposes sensitive tools or data.
+- **Input Validation**: Ensure your MCP server validates all incoming requests and parameters.
+
+For a comprehensive guide on securing your MCP integrations, please refer to our [Security Considerations](./security.mdx) page and the official [MCP Transport Security documentation](https://modelcontextprotocol.io/docs/concepts/transports#security-considerations).

docs/observability/portkey.mdx

@@ -7,196 +7,818 @@ icon: key
 <img src="https://raw.githubusercontent.com/siddharthsambharia-portkey/Portkey-Product-Images/main/Portkey-CrewAI.png" alt="Portkey CrewAI Header Image" width="70%" />
 
 
-[Portkey](https://portkey.ai/?utm_source=crewai&utm_medium=crewai&utm_campaign=crewai) is a 2-line upgrade to make your CrewAI agents reliable, cost-efficient, and fast.
 
-Portkey adds 4 core production capabilities to any CrewAI agent:
-1. Routing to **200+ LLMs**
-2. Making each LLM call more robust
-3. Full-stack tracing & cost, performance analytics
-4. Real-time guardrails to enforce behavior
+## Introduction
 
-## Getting Started
+Portkey enhances CrewAI with production-readiness features, turning your experimental agent crews into robust systems by providing:
+
+- **Complete observability** of every agent step, tool use, and interaction
+- **Built-in reliability** with fallbacks, retries, and load balancing
+- **Cost tracking and optimization** to manage your AI spend
+- **Access to 200+ LLMs** through a single integration
+- **Guardrails** to keep agent behavior safe and compliant
+- **Version-controlled prompts** for consistent agent performance
+
+
+### Installation & Setup
 
 <Steps>
-    <Step title="Install CrewAI and Portkey">
-    ```bash
-    pip install -qU crewai portkey-ai
-    ```
-    </Step>
-    <Step title="Configure the LLM Client">
-    To build CrewAI Agents with Portkey, you'll need two keys:
-    - **Portkey API Key**: Sign up on the [Portkey app](https://app.portkey.ai/?utm_source=crewai&utm_medium=crewai&utm_campaign=crewai) and copy your API key
-    - **Virtual Key**: Virtual Keys securely manage your LLM API keys in one place. Store your LLM provider API keys securely in Portkey's vault
+<Step title="Install the required packages">
+```bash
+pip install -U crewai portkey-ai
+```
+</Step>
 
-    ```python
-    from crewai import LLM
-    from portkey_ai import createHeaders, PORTKEY_GATEWAY_URL
+<Step title="Generate API Key" icon="lock">
+Create a Portkey API key with optional budget/rate limits from the [Portkey dashboard](https://app.portkey.ai/). You can also attach configurations for reliability, caching, and more to this key. More on this later.
+</Step>
 
-    gpt_llm = LLM(
-        model="gpt-4",
-        base_url=PORTKEY_GATEWAY_URL,
-        api_key="dummy", # We are using Virtual key
-        extra_headers=createHeaders(
-            api_key="YOUR_PORTKEY_API_KEY",
-            virtual_key="YOUR_VIRTUAL_KEY", # Enter your Virtual key from Portkey
-        )
-    )
-    ```
-    </Step>
-    <Step title="Create and Run Your First Agent">
-    ```python
-    from crewai import Agent, Task, Crew
-
-    # Define your agents with roles and goals
-    coder = Agent(
-        role='Software developer',
-        goal='Write clear, concise code on demand',
-        backstory='An expert coder with a keen eye for software trends.',
-        llm=gpt_llm
-    )
-
-    # Create tasks for your agents
-    task1 = Task(
-        description="Define the HTML for making a simple website with heading- Hello World! Portkey is working!",
-        expected_output="A clear and concise HTML code",
-        agent=coder
-    )
-
-    # Instantiate your crew
-    crew = Crew(
-        agents=[coder],
-        tasks=[task1],
-    )
-
-    result = crew.kickoff()
-    print(result)
-    ```
-    </Step>
-</Steps>
-
-## Key Features
-
-| Feature | Description |
-|:--------|:------------|
-| 🌐 Multi-LLM Support | Access OpenAI, Anthropic, Gemini, Azure, and 250+ providers through a unified interface |
-| 🛡️ Production Reliability | Implement retries, timeouts, load balancing, and fallbacks |
-| 📊 Advanced Observability | Track 40+ metrics including costs, tokens, latency, and custom metadata |
-| 🔍 Comprehensive Logging | Debug with detailed execution traces and function call logs |
-| 🚧 Security Controls | Set budget limits and implement role-based access control |
-| 🔄 Performance Analytics | Capture and analyze feedback for continuous improvement |
-| 💾 Intelligent Caching | Reduce costs and latency with semantic or simple caching |
-
-
-## Production Features with Portkey Configs
-
-All features mentioned below are through Portkey's Config system. Portkey's Config system allows you to define routing strategies using simple JSON objects in your LLM API calls. You can create and manage Configs directly in your code or through the Portkey Dashboard. Each Config has a unique ID for easy reference.
-
-<Frame>
-    <img src="https://raw.githubusercontent.com/Portkey-AI/docs-core/refs/heads/main/images/libraries/libraries-3.avif"/>
-</Frame>
-
-
-### 1. Use 250+ LLMs
-Access various LLMs like Anthropic, Gemini, Mistral, Azure OpenAI, and more with minimal code changes. Switch between providers or use them together seamlessly. [Learn more about Universal API](https://portkey.ai/docs/product/ai-gateway/universal-api)
-
-
-Easily switch between different LLM providers:
+<Step title="Configure CrewAI with Portkey">
+The integration is simple - you just need to update the LLM configuration in your CrewAI setup:
 
 ```python
-# Anthropic Configuration
-anthropic_llm = LLM(
-    model="claude-3-5-sonnet-latest",
+from crewai import LLM
+from portkey_ai import createHeaders, PORTKEY_GATEWAY_URL
+
+# Create an LLM instance with Portkey integration
+gpt_llm = LLM(
+    model="gpt-4o",
     base_url=PORTKEY_GATEWAY_URL,
-    api_key="dummy",
+    api_key="dummy",  # We are using a Virtual key, so this is a placeholder
     extra_headers=createHeaders(
         api_key="YOUR_PORTKEY_API_KEY",
-        virtual_key="YOUR_ANTHROPIC_VIRTUAL_KEY", #You don't need provider when using Virtual keys
-        trace_id="anthropic_agent"
+        virtual_key="YOUR_LLM_VIRTUAL_KEY",
+        trace_id="unique-trace-id",               # Optional, for request tracing
     )
 )
 
-# Azure OpenAI Configuration
-azure_llm = LLM(
-    model="gpt-4",
+#Use them in your Crew Agents like this:
+
+	@agent
+	def lead_market_analyst(self) -> Agent:
+		return Agent(
+			config=self.agents_config['lead_market_analyst'],
+			verbose=True,
+			memory=False,
+			llm=gpt_llm
+		)
+
+```
+
+<Info>
+**What are Virtual Keys?** Virtual keys in Portkey securely store your LLM provider API keys (OpenAI, Anthropic, etc.) in an encrypted vault. They allow for easier key rotation and budget management. [Learn more about virtual keys here](https://portkey.ai/docs/product/ai-gateway/virtual-keys).
+</Info>
+</Step>
+</Steps>
+
+## Production Features
+
+### 1. Enhanced Observability
+
+Portkey provides comprehensive observability for your CrewAI agents, helping you understand exactly what's happening during each execution.
+
+<Tabs>
+  <Tab title="Traces">
+<Frame>
+    <img src="https://raw.githubusercontent.com/siddharthsambharia-portkey/Portkey-Product-Images/refs/heads/main/CrewAI%20Product%2011.1.webp"/>
+</Frame>
+
+Traces provide a hierarchical view of your crew's execution, showing the sequence of LLM calls, tool invocations, and state transitions.
+
+```python
+# Add trace_id to enable hierarchical tracing in Portkey
+portkey_llm = LLM(
+    model="gpt-4o",
     base_url=PORTKEY_GATEWAY_URL,
     api_key="dummy",
     extra_headers=createHeaders(
         api_key="YOUR_PORTKEY_API_KEY",
-        virtual_key="YOUR_AZURE_VIRTUAL_KEY", #You don't need provider when using Virtual keys
-        trace_id="azure_agent"
+        virtual_key="YOUR_OPENAI_VIRTUAL_KEY",
+        trace_id="unique-session-id"  # Add unique trace ID
+    )
+)
+```
+  </Tab>
+
+  <Tab title="Logs">
+<Frame>
+    <img src="https://raw.githubusercontent.com/siddharthsambharia-portkey/Portkey-Product-Images/refs/heads/main/CrewAI%20Portkey%20Docs%20Metadata.png"/>
+</Frame>
+
+Portkey logs every interaction with LLMs, including:
+
+- Complete request and response payloads
+- Latency and token usage metrics
+- Cost calculations
+- Tool calls and function executions
+
+All logs can be filtered by metadata, trace IDs, models, and more, making it easy to debug specific crew runs.
+  </Tab>
+
+  <Tab title="Metrics & Dashboards">
+<Frame>
+    <img src="https://raw.githubusercontent.com/siddharthsambharia-portkey/Portkey-Product-Images/refs/heads/main/CrewAI%20Dashboard.png"/>
+</Frame>
+
+Portkey provides built-in dashboards that help you:
+
+- Track cost and token usage across all crew runs
+- Analyze performance metrics like latency and success rates
+- Identify bottlenecks in your agent workflows
+- Compare different crew configurations and LLMs
+
+You can filter and segment all metrics by custom metadata to analyze specific crew types, user groups, or use cases.
+  </Tab>
+
+  <Tab title="Metadata Filtering">
+<Frame>
+  <img src="https://raw.githubusercontent.com/siddharthsambharia-portkey/Portkey-Product-Images/refs/heads/main/Metadata%20Filters%20from%20CrewAI.png" alt="Analytics with metadata filters" />
+</Frame>
+
+Add custom metadata to your CrewAI LLM configuration to enable powerful filtering and segmentation:
+
+```python
+portkey_llm = LLM(
+    model="gpt-4o",
+    base_url=PORTKEY_GATEWAY_URL,
+    api_key="dummy",
+    extra_headers=createHeaders(
+        api_key="YOUR_PORTKEY_API_KEY",
+        virtual_key="YOUR_OPENAI_VIRTUAL_KEY",
+        metadata={
+            "crew_type": "research_crew",
+            "environment": "production",
+            "_user": "user_123",   # Special _user field for user analytics
+            "request_source": "mobile_app"
+        }
     )
 )
 ```
 
+This metadata can be used to filter logs, traces, and metrics on the Portkey dashboard, allowing you to analyze specific crew runs, users, or environments.
+  </Tab>
+</Tabs>
 
-### 2. Caching
-Improve response times and reduce costs with two powerful caching modes:
-- **Simple Cache**: Perfect for exact matches
-- **Semantic Cache**: Matches responses for requests that are semantically similar
-[Learn more about Caching](https://portkey.ai/docs/product/ai-gateway/cache-simple-and-semantic)
+### 2. Reliability - Keep Your Crews Running Smoothly
 
-```py
-config = {
-    "cache": {
-        "mode": "semantic",  # or "simple" for exact matching
+When running crews in production, things can go wrong - API rate limits, network issues, or provider outages. Portkey's reliability features ensure your agents keep running smoothly even when problems occur.
+
+It's simple to enable fallback in your CrewAI setup by using a Portkey Config:
+
+```python
+from crewai import LLM
+from portkey_ai import createHeaders, PORTKEY_GATEWAY_URL
+
+# Create LLM with fallback configuration
+portkey_llm = LLM(
+    model="gpt-4o",
+    max_tokens=1000,
+    base_url=PORTKEY_GATEWAY_URL,
+    api_key="dummy",
+    extra_headers=createHeaders(
+        api_key="YOUR_PORTKEY_API_KEY",
+        config={
+            "strategy": {
+                "mode": "fallback"
+            },
+            "targets": [
+                {
+                    "provider": "openai",
+                    "api_key": "YOUR_OPENAI_API_KEY",
+                    "override_params": {"model": "gpt-4o"}
+                },
+                {
+                    "provider": "anthropic",
+                    "api_key": "YOUR_ANTHROPIC_API_KEY",
+                    "override_params": {"model": "claude-3-opus-20240229"}
+                }
+            ]
+        }
+    )
+)
+
+# Use this LLM configuration with your agents
+```
+
+This configuration will automatically try Claude if the GPT-4o request fails, ensuring your crew can continue operating.
+
+<CardGroup cols="2">
+  <Card title="Automatic Retries" icon="rotate" href="https://portkey.ai/docs/product/ai-gateway/automatic-retries">
+    Handles temporary failures automatically. If an LLM call fails, Portkey will retry the same request for the specified number of times - perfect for rate limits or network blips.
+  </Card>
+  <Card title="Request Timeouts" icon="clock" href="https://portkey.ai/docs/product/ai-gateway/request-timeouts">
+    Prevent your agents from hanging. Set timeouts to ensure you get responses (or can fail gracefully) within your required timeframes.
+  </Card>
+  <Card title="Conditional Routing" icon="route" href="https://portkey.ai/docs/product/ai-gateway/conditional-routing">
+    Send different requests to different providers. Route complex reasoning to GPT-4, creative tasks to Claude, and quick responses to Gemini based on your needs.
+  </Card>
+  <Card title="Fallbacks" icon="shield" href="https://portkey.ai/docs/product/ai-gateway/fallbacks">
+    Keep running even if your primary provider fails. Automatically switch to backup providers to maintain availability.
+  </Card>
+  <Card title="Load Balancing" icon="scale-balanced" href="https://portkey.ai/docs/product/ai-gateway/load-balancing">
+    Spread requests across multiple API keys or providers. Great for high-volume crew operations and staying within rate limits.
+  </Card>
+</CardGroup>
+
+### 3. Prompting in CrewAI
+
+Portkey's Prompt Engineering Studio helps you create, manage, and optimize the prompts used in your CrewAI agents. Instead of hardcoding prompts or instructions, use Portkey's prompt rendering API to dynamically fetch and apply your versioned prompts.
+
+<Frame caption="Manage prompts in Portkey's Prompt Library">
+![Prompt Playground Interface](https://raw.githubusercontent.com/siddharthsambharia-portkey/Portkey-Product-Images/refs/heads/main/CrewAI%20Portkey%20Docs.webp)
+</Frame>
+
+<Tabs>
+  <Tab title="Prompt Playground">
+Prompt Playground is a place to compare, test and deploy perfect prompts for your AI application. It's where you experiment with different models, test variables, compare outputs, and refine your prompt engineering strategy before deploying to production. It allows you to:
+
+1. Iteratively develop prompts before using them in your agents
+2. Test prompts with different variables and models
+3. Compare outputs between different prompt versions
+4. Collaborate with team members on prompt development
+
+This visual environment makes it easier to craft effective prompts for each step in your CrewAI agents' workflow.
+  </Tab>
+
+  <Tab title="Using Prompt Templates">
+The Prompt Render API retrieves your prompt templates with all parameters configured:
+
+```python
+from crewai import Agent, LLM
+from portkey_ai import createHeaders, PORTKEY_GATEWAY_URL, Portkey
+
+# Initialize Portkey admin client
+portkey_admin = Portkey(api_key="YOUR_PORTKEY_API_KEY")
+
+# Retrieve prompt using the render API
+prompt_data = portkey_client.prompts.render(
+    prompt_id="YOUR_PROMPT_ID",
+    variables={
+        "agent_role": "Senior Research Scientist",
     }
+)
+
+backstory_agent_prompt=prompt_data.data.messages[0]["content"]
+
+
+# Set up LLM with Portkey integration
+portkey_llm = LLM(
+    model="gpt-4o",
+    base_url=PORTKEY_GATEWAY_URL,
+    api_key="dummy",
+    extra_headers=createHeaders(
+        api_key="YOUR_PORTKEY_API_KEY",
+        virtual_key="YOUR_OPENAI_VIRTUAL_KEY"
+    )
+)
+
+# Create agent using the rendered prompt
+researcher = Agent(
+    role="Senior Research Scientist",
+    goal="Discover groundbreaking insights about the assigned topic",
+    backstory=backstory_agent,  # Use the rendered prompt
+    verbose=True,
+    llm=portkey_llm
+)
+```
+  </Tab>
+
+  <Tab title="Prompt Versioning">
+You can:
+- Create multiple versions of the same prompt
+- Compare performance between versions
+- Roll back to previous versions if needed
+- Specify which version to use in your code:
+
+```python
+# Use a specific prompt version
+prompt_data = portkey_admin.prompts.render(
+    prompt_id="YOUR_PROMPT_ID@version_number",
+    variables={
+        "agent_role": "Senior Research Scientist",
+        "agent_goal": "Discover groundbreaking insights"
+    }
+)
+```
+  </Tab>
+
+  <Tab title="Mustache Templating for variables">
+Portkey prompts use Mustache-style templating for easy variable substitution:
+
+```
+You are a {{agent_role}} with expertise in {{domain}}.
+
+Your mission is to {{agent_goal}} by leveraging your knowledge
+and experience in the field.
+
+Always maintain a {{tone}} tone and focus on providing {{focus_area}}.
+```
+
+When rendering, simply pass the variables:
+
+```python
+prompt_data = portkey_admin.prompts.render(
+    prompt_id="YOUR_PROMPT_ID",
+    variables={
+        "agent_role": "Senior Research Scientist",
+        "domain": "artificial intelligence",
+        "agent_goal": "discover groundbreaking insights",
+        "tone": "professional",
+        "focus_area": "practical applications"
+    }
+)
+```
+  </Tab>
+</Tabs>
+
+<Card title="Prompt Engineering Studio" icon="wand-magic-sparkles" href="https://portkey.ai/docs/product/prompt-library">
+  Learn more about Portkey's prompt management features
+</Card>
+
+### 4. Guardrails for Safe Crews
+
+Guardrails ensure your CrewAI agents operate safely and respond appropriately in all situations.
+
+**Why Use Guardrails?**
+
+CrewAI agents can experience various failure modes:
+- Generating harmful or inappropriate content
+- Leaking sensitive information like PII
+- Hallucinating incorrect information
+- Generating outputs in incorrect formats
+
+Portkey's guardrails add protections for both inputs and outputs.
+
+**Implementing Guardrails**
+
+```python
+from crewai import Agent, LLM
+from portkey_ai import createHeaders, PORTKEY_GATEWAY_URL
+
+# Create LLM with guardrails
+portkey_llm = LLM(
+    model="gpt-4o",
+    base_url=PORTKEY_GATEWAY_URL,
+    api_key="dummy",
+    extra_headers=createHeaders(
+        api_key="YOUR_PORTKEY_API_KEY",
+        virtual_key="YOUR_OPENAI_VIRTUAL_KEY",
+        config={
+            "input_guardrails": ["guardrails-id-xxx", "guardrails-id-yyy"],
+            "output_guardrails": ["guardrails-id-zzz"]
+        }
+    )
+)
+
+# Create agent with guardrailed LLM
+researcher = Agent(
+    role="Senior Research Scientist",
+    goal="Discover groundbreaking insights about the assigned topic",
+    backstory="You are an expert researcher with deep domain knowledge.",
+    verbose=True,
+    llm=portkey_llm
+)
+```
+
+Portkey's guardrails can:
+- Detect and redact PII in both inputs and outputs
+- Filter harmful or inappropriate content
+- Validate response formats against schemas
+- Check for hallucinations against ground truth
+- Apply custom business logic and rules
+
+<Card title="Learn More About Guardrails" icon="shield-check" href="https://portkey.ai/docs/product/guardrails">
+  Explore Portkey's guardrail features to enhance agent safety
+</Card>
+
+### 5. User Tracking with Metadata
+
+Track individual users through your CrewAI agents using Portkey's metadata system.
+
+**What is Metadata in Portkey?**
+
+Metadata allows you to associate custom data with each request, enabling filtering, segmentation, and analytics. The special `_user` field is specifically designed for user tracking.
+
+```python
+from crewai import Agent, LLM
+from portkey_ai import createHeaders, PORTKEY_GATEWAY_URL
+
+# Configure LLM with user tracking
+portkey_llm = LLM(
+    model="gpt-4o",
+    base_url=PORTKEY_GATEWAY_URL,
+    api_key="dummy",
+    extra_headers=createHeaders(
+        api_key="YOUR_PORTKEY_API_KEY",
+        virtual_key="YOUR_OPENAI_VIRTUAL_KEY",
+        metadata={
+            "_user": "user_123",  # Special _user field for user analytics
+            "user_tier": "premium",
+            "user_company": "Acme Corp",
+            "session_id": "abc-123"
+        }
+    )
+)
+
+# Create agent with tracked LLM
+researcher = Agent(
+    role="Senior Research Scientist",
+    goal="Discover groundbreaking insights about the assigned topic",
+    backstory="You are an expert researcher with deep domain knowledge.",
+    verbose=True,
+    llm=portkey_llm
+)
+```
+
+**Filter Analytics by User**
+
+With metadata in place, you can filter analytics by user and analyze performance metrics on a per-user basis:
+
+<Frame caption="Filter analytics by user">
+  <img src="https://raw.githubusercontent.com/siddharthsambharia-portkey/Portkey-Product-Images/refs/heads/main/Metadata%20Filters%20from%20CrewAI.png"/>
+</Frame>
+
+This enables:
+- Per-user cost tracking and budgeting
+- Personalized user analytics
+- Team or organization-level metrics
+- Environment-specific monitoring (staging vs. production)
+
+<Card title="Learn More About Metadata" icon="tags" href="https://portkey.ai/docs/product/observability/metadata">
+  Explore how to use custom metadata to enhance your analytics
+</Card>
+
+### 6. Caching for Efficient Crews
+
+Implement caching to make your CrewAI agents more efficient and cost-effective:
+
+<Tabs>
+  <Tab title="Simple Caching">
+```python
+from crewai import Agent, LLM
+from portkey_ai import createHeaders, PORTKEY_GATEWAY_URL
+
+# Configure LLM with simple caching
+portkey_llm = LLM(
+    model="gpt-4o",
+    base_url=PORTKEY_GATEWAY_URL,
+    api_key="dummy",
+    extra_headers=createHeaders(
+        api_key="YOUR_PORTKEY_API_KEY",
+        virtual_key="YOUR_OPENAI_VIRTUAL_KEY",
+        config={
+            "cache": {
+                "mode": "simple"
+            }
+        }
+    )
+)
+
+# Create agent with cached LLM
+researcher = Agent(
+    role="Senior Research Scientist",
+    goal="Discover groundbreaking insights about the assigned topic",
+    backstory="You are an expert researcher with deep domain knowledge.",
+    verbose=True,
+    llm=portkey_llm
+)
+```
+
+Simple caching performs exact matches on input prompts, caching identical requests to avoid redundant model executions.
+  </Tab>
+
+  <Tab title="Semantic Caching">
+```python
+from crewai import Agent, LLM
+from portkey_ai import createHeaders, PORTKEY_GATEWAY_URL
+
+# Configure LLM with semantic caching
+portkey_llm = LLM(
+    model="gpt-4o",
+    base_url=PORTKEY_GATEWAY_URL,
+    api_key="dummy",
+    extra_headers=createHeaders(
+        api_key="YOUR_PORTKEY_API_KEY",
+        virtual_key="YOUR_OPENAI_VIRTUAL_KEY",
+        config={
+            "cache": {
+                "mode": "semantic"
+            }
+        }
+    )
+)
+
+# Create agent with semantically cached LLM
+researcher = Agent(
+    role="Senior Research Scientist",
+    goal="Discover groundbreaking insights about the assigned topic",
+    backstory="You are an expert researcher with deep domain knowledge.",
+    verbose=True,
+    llm=portkey_llm
+)
+```
+
+Semantic caching considers the contextual similarity between input requests, caching responses for semantically similar inputs.
+  </Tab>
+</Tabs>
+
+### 7. Model Interoperability
+
+CrewAI supports multiple LLM providers, and Portkey extends this capability by providing access to over 200 LLMs through a unified interface. You can easily switch between different models without changing your core agent logic:
+
+```python
+from crewai import Agent, LLM
+from portkey_ai import createHeaders, PORTKEY_GATEWAY_URL
+
+# Set up LLMs with different providers
+openai_llm = LLM(
+    model="gpt-4o",
+    base_url=PORTKEY_GATEWAY_URL,
+    api_key="dummy",
+    extra_headers=createHeaders(
+        api_key="YOUR_PORTKEY_API_KEY",
+        virtual_key="YOUR_OPENAI_VIRTUAL_KEY"
+    )
+)
+
+anthropic_llm = LLM(
+    model="claude-3-5-sonnet-latest",
+    max_tokens=1000,
+    base_url=PORTKEY_GATEWAY_URL,
+    api_key="dummy",
+    extra_headers=createHeaders(
+        api_key="YOUR_PORTKEY_API_KEY",
+        virtual_key="YOUR_ANTHROPIC_VIRTUAL_KEY"
+    )
+)
+
+# Choose which LLM to use for each agent based on your needs
+researcher = Agent(
+    role="Senior Research Scientist",
+    goal="Discover groundbreaking insights about the assigned topic",
+    backstory="You are an expert researcher with deep domain knowledge.",
+    verbose=True,
+    llm=openai_llm  # Use anthropic_llm for Anthropic
+)
+```
+
+Portkey provides access to LLMs from providers including:
+
+- OpenAI (GPT-4o, GPT-4 Turbo, etc.)
+- Anthropic (Claude 3.5 Sonnet, Claude 3 Opus, etc.)
+- Mistral AI (Mistral Large, Mistral Medium, etc.)
+- Google Vertex AI (Gemini 1.5 Pro, etc.)
+- Cohere (Command, Command-R, etc.)
+- AWS Bedrock (Claude, Titan, etc.)
+- Local/Private Models
+
+<Card title="Supported Providers" icon="server" href="https://portkey.ai/docs/integrations/llms">
+  See the full list of LLM providers supported by Portkey
+</Card>
+
+## Set Up Enterprise Governance for CrewAI
+
+**Why Enterprise Governance?**
+If you are using CrewAI inside your organization, you need to consider several governance aspects:
+- **Cost Management**: Controlling and tracking AI spending across teams
+- **Access Control**: Managing which teams can use specific models
+- **Usage Analytics**: Understanding how AI is being used across the organization
+- **Security & Compliance**: Maintaining enterprise security standards
+- **Reliability**: Ensuring consistent service across all users
+
+Portkey adds a comprehensive governance layer to address these enterprise needs. Let's implement these controls step by step.
+
+<Steps>
+<Step title="Create Virtual Key">
+Virtual Keys are Portkey's secure way to manage your LLM provider API keys. They provide essential controls like:
+- Budget limits for API usage
+- Rate limiting capabilities
+- Secure API key storage
+
+To create a virtual key:
+Go to [Virtual Keys](https://app.portkey.ai/virtual-keys) in the Portkey App. Save and copy the virtual key ID
+
+<Frame>
+<img src="https://raw.githubusercontent.com/siddharthsambharia-portkey/Portkey-Product-Images/refs/heads/main/Virtual%20Key%20from%20Portkey%20Docs.png" width="500"/>
+</Frame>
+
+<Note>
+Save your virtual key ID - you'll need it for the next step.
+</Note>
+</Step>
+
+<Step title="Create Default Config">
+Configs in Portkey define how your requests are routed, with features like advanced routing, fallbacks, and retries.
+
+To create your config:
+1. Go to [Configs](https://app.portkey.ai/configs) in Portkey dashboard
+2. Create new config with:
+    ```json
+    {
+        "virtual_key": "YOUR_VIRTUAL_KEY_FROM_STEP1",
+       	"override_params": {
+          "model": "gpt-4o" // Your preferred model name
+        }
+    }
+    ```
+3. Save and note the Config name for the next step
+
+<Frame>
+<img src="https://raw.githubusercontent.com/siddharthsambharia-portkey/Portkey-Product-Images/refs/heads/main/CrewAI%20Portkey%20Docs%20Config.png" width="500"/>
+
+</Frame>
+</Step>
+
+<Step title="Configure Portkey API Key">
+Now create a Portkey API key and attach the config you created in Step 2:
+
+1. Go to [API Keys](https://app.portkey.ai/api-keys) in Portkey and Create new API key
+2. Select your config from `Step 2`
+3. Generate and save your API key
+
+<Frame>
+<img src="https://raw.githubusercontent.com/siddharthsambharia-portkey/Portkey-Product-Images/refs/heads/main/CrewAI%20API%20Key.png" width="500"/>
+
+</Frame>
+</Step>
+
+<Step title="Connect to CrewAI">
+After setting up your Portkey API key with the attached config, connect it to your CrewAI agents:
+
+```python
+from crewai import Agent, LLM
+from portkey_ai import PORTKEY_GATEWAY_URL
+
+# Configure LLM with your API key
+portkey_llm = LLM(
+    model="gpt-4o",
+    base_url=PORTKEY_GATEWAY_URL,
+    api_key="YOUR_PORTKEY_API_KEY"
+)
+
+# Create agent with Portkey-enabled LLM
+researcher = Agent(
+    role="Senior Research Scientist",
+    goal="Discover groundbreaking insights about the assigned topic",
+    backstory="You are an expert researcher with deep domain knowledge.",
+    verbose=True,
+    llm=portkey_llm
+)
+```
+</Step>
+</Steps>
+
+<AccordionGroup>
+  <Accordion title="Step 1: Implement Budget Controls & Rate Limits">
+### Step 1: Implement Budget Controls & Rate Limits
+
+Virtual Keys enable granular control over LLM access at the team/department level. This helps you:
+- Set up [budget limits](https://portkey.ai/docs/product/ai-gateway/virtual-keys/budget-limits)
+- Prevent unexpected usage spikes using Rate limits
+- Track departmental spending
+
+#### Setting Up Department-Specific Controls:
+1. Navigate to [Virtual Keys](https://app.portkey.ai/virtual-keys) in Portkey dashboard
+2. Create new Virtual Key for each department with budget limits and rate limits
+3. Configure department-specific limits
+
+<Frame>
+<img src="https://raw.githubusercontent.com/siddharthsambharia-portkey/Portkey-Product-Images/refs/heads/main/Virtual%20Key%20from%20Portkey%20Docs.png" width="500"/>
+</Frame>
+  </Accordion>
+
+  <Accordion title="Step 2: Define Model Access Rules">
+### Step 2: Define Model Access Rules
+
+As your AI usage scales, controlling which teams can access specific models becomes crucial. Portkey Configs provide this control layer with features like:
+
+#### Access Control Features:
+- **Model Restrictions**: Limit access to specific models
+- **Data Protection**: Implement guardrails for sensitive data
+- **Reliability Controls**: Add fallbacks and retry logic
+
+#### Example Configuration:
+Here's a basic configuration to route requests to OpenAI, specifically using GPT-4o:
+
+```json
+{
+	"strategy": {
+		"mode": "single"
+	},
+	"targets": [
+		{
+			"virtual_key": "YOUR_OPENAI_VIRTUAL_KEY",
+			"override_params": {
+				"model": "gpt-4o"
+			}
+		}
+	]
 }
 ```
 
-### 3. Production Reliability
-Portkey provides comprehensive reliability features:
-- **Automatic Retries**: Handle temporary failures gracefully
-- **Request Timeouts**: Prevent hanging operations
-- **Conditional Routing**: Route requests based on specific conditions
-- **Fallbacks**: Set up automatic provider failovers
-- **Load Balancing**: Distribute requests efficiently
+  Create your config on the [Configs page](https://app.portkey.ai/configs) in your Portkey dashboard.
 
-[Learn more about Reliability Features](https://portkey.ai/docs/product/ai-gateway/)
+    <Note>
+    Configs can be updated anytime to adjust controls without affecting running applications.
+    </Note>
+  </Accordion>
 
+  <Accordion title="Step 3: Implement Access Controls">
+    ### Step 3: Implement Access Controls
 
+    Create User-specific API keys that automatically:
+    - Track usage per user/team with the help of virtual keys
+    - Apply appropriate configs to route requests
+    - Collect relevant metadata to filter logs
+    - Enforce access permissions
 
-### 4. Metrics
+    Create API keys through:
+    - [Portkey App](https://app.portkey.ai/)
+    - [API Key Management API](/api-reference/admin-api/control-plane/api-keys/create-api-key)
 
-Agent runs are complex. Portkey automatically logs **40+ comprehensive metrics** for your AI agents, including cost, tokens used, latency, etc. Whether you need a broad overview or granular insights into your agent runs, Portkey's customizable filters provide the metrics you need.
+    Example using Python SDK:
+    ```python
+    from portkey_ai import Portkey
 
+    portkey = Portkey(api_key="YOUR_ADMIN_API_KEY")
 
-- Cost per agent interaction
-- Response times and latency
-- Token usage and efficiency
-- Success/failure rates
-- Cache hit rates
+    api_key = portkey.api_keys.create(
+        name="engineering-team",
+        type="organisation",
+        workspace_id="YOUR_WORKSPACE_ID",
+        defaults={
+            "config_id": "your-config-id",
+            "metadata": {
+                "environment": "production",
+                "department": "engineering"
+            }
+        },
+        scopes=["logs.view", "configs.read"]
+    )
+    ```
 
-<img src="https://github.com/siddharthsambharia-portkey/Portkey-Product-Images/blob/main/Portkey-Dashboard.png?raw=true" width="70%" alt="Portkey Dashboard" />
+    For detailed key management instructions, see our [API Keys documentation](/api-reference/admin-api/control-plane/api-keys/create-api-key).
+  </Accordion>
 
-### 5. Detailed Logging
-Logs are essential for understanding agent behavior, diagnosing issues, and improving performance. They provide a detailed record of agent activities and tool use, which is crucial for debugging and optimizing processes.
+  <Accordion title="Step 4: Deploy & Monitor">
+    ### Step 4: Deploy & Monitor
+    After distributing API keys to your team members, your enterprise-ready CrewAI setup is ready to go. Each team member can now use their designated API keys with appropriate access levels and budget controls.
 
+    Monitor usage in Portkey dashboard:
+    - Cost tracking by department
+    - Model usage patterns
+    - Request volumes
+    - Error rates
+  </Accordion>
 
-Access a dedicated section to view records of agent executions, including parameters, outcomes, function calls, and errors. Filter logs based on multiple parameters such as trace ID, model, tokens used, and metadata.
+</AccordionGroup>
 
-<details>
-  <summary><b>Traces</b></summary>
-  <img src="https://raw.githubusercontent.com/siddharthsambharia-portkey/Portkey-Product-Images/main/Portkey-Traces.png" alt="Portkey Traces" width="70%" />
-</details>
+<Note>
+### Enterprise Features Now Available
+**Your CrewAI integration now has:**
+- Departmental budget controls
+- Model access governance
+- Usage tracking & attribution
+- Security guardrails
+- Reliability features
+</Note>
 
-<details>
-  <summary><b>Logs</b></summary>
-  <img src="https://raw.githubusercontent.com/siddharthsambharia-portkey/Portkey-Product-Images/main/Portkey-Logs.png" alt="Portkey Logs" width="70%" />
-</details>
+## Frequently Asked Questions
 
-### 6. Enterprise Security Features
-- Set budget limit and rate limts per Virtual Key (disposable API keys)
-- Implement role-based access control
-- Track system changes with audit logs
-- Configure data retention policies
+<AccordionGroup>
+  <Accordion title="How does Portkey enhance CrewAI?">
+    Portkey adds production-readiness to CrewAI through comprehensive observability (traces, logs, metrics), reliability features (fallbacks, retries, caching), and access to 200+ LLMs through a unified interface. This makes it easier to debug, optimize, and scale your agent applications.
+  </Accordion>
 
+  <Accordion title="Can I use Portkey with existing CrewAI applications?">
+    Yes! Portkey integrates seamlessly with existing CrewAI applications. You just need to update your LLM configuration code with the Portkey-enabled version. The rest of your agent and crew code remains unchanged.
+  </Accordion>
 
+  <Accordion title="Does Portkey work with all CrewAI features?">
+    Portkey supports all CrewAI features, including agents, tools, human-in-the-loop workflows, and all task process types (sequential, hierarchical, etc.). It adds observability and reliability without limiting any of the framework's functionality.
+  </Accordion>
 
-For detailed information on creating and managing Configs, visit the [Portkey documentation](https://docs.portkey.ai/product/ai-gateway/configs).
+  <Accordion title="Can I track usage across multiple agents in a crew?">
+    Yes, Portkey allows you to use a consistent `trace_id` across multiple agents in a crew to track the entire workflow. This is especially useful for complex crews where you want to understand the full execution path across multiple agents.
+  </Accordion>
+
+  <Accordion title="How do I filter logs and traces for specific crew runs?">
+    Portkey allows you to add custom metadata to your LLM configuration, which you can then use for filtering. Add fields like `crew_name`, `crew_type`, or `session_id` to easily find and analyze specific crew executions.
+  </Accordion>
+
+  <Accordion title="Can I use my own API keys with Portkey?">
+    Yes! Portkey uses your own API keys for the various LLM providers. It securely stores them as virtual keys, allowing you to easily manage and rotate keys without changing your code.
+  </Accordion>
+
+</AccordionGroup>
 
 ## Resources
 
-- [📘 Portkey Documentation](https://docs.portkey.ai)
-- [📊 Portkey Dashboard](https://app.portkey.ai/?utm_source=crewai&utm_medium=crewai&utm_campaign=crewai)
-- [🐦 Twitter](https://twitter.com/portkeyai)
-- [💬 Discord Community](https://discord.gg/DD7vgKK299)
+<CardGroup cols="3">
+  <Card title="CrewAI Docs" icon="book" href="https://docs.crewai.com/">
+    <p>Official CrewAI documentation</p>
+  </Card>
+  <Card title="Book a Demo" icon="calendar" href="https://calendly.com/portkey-ai">
+    <p>Get personalized guidance on implementing this integration</p>
+  </Card>
+</CardGroup>

pyproject.toml

@@ -1,9 +1,9 @@
 [project]
 name = "crewai"
-version = "0.121.0"
+version = "0.121.1"
 description = "Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks."
 readme = "README.md"
-requires-python = ">=3.10,<3.13"
+requires-python = ">=3.10,<3.14"
 authors = [
     { name = "Joao Moura", email = "joao@crewai.com" }
 ]
@@ -22,6 +22,8 @@ dependencies = [
     "opentelemetry-exporter-otlp-proto-http>=1.30.0",
     # Data Handling
     "chromadb>=0.5.23",
+    "tokenizers>=0.20.3",
+    "onnxruntime==1.22.0",
     "openpyxl>=3.1.5",
     "pyvis>=0.3.2",
     # Authentication and Security
@@ -47,10 +49,9 @@ Repository = "https://github.com/crewAIInc/crewAI"
 [project.optional-dependencies]
 tools = ["crewai-tools~=0.45.0"]
 embeddings = [
-    "tiktoken~=0.7.0"
+    "tiktoken~=0.8.0"
 ]
 agentops = ["agentops>=0.3.0"]
-fastembed = ["fastembed>=0.4.1"]
 pdfplumber = [
     "pdfplumber>=0.11.4",
 ]
@@ -100,6 +101,27 @@ exclude = ["cli/templates"]
 [tool.bandit]
 exclude_dirs = ["src/crewai/cli/templates"]
 
+# PyTorch index configuration, since torch 2.5.0 is not compatible with python 3.13
+[[tool.uv.index]]
+name = "pytorch-nightly"
+url = "https://download.pytorch.org/whl/nightly/cpu"
+explicit = true
+
+[[tool.uv.index]]
+name = "pytorch"
+url = "https://download.pytorch.org/whl/cpu"
+explicit = true
+
+[tool.uv.sources]
+torch = [
+  { index = "pytorch-nightly", marker = "python_version >= '3.13'" },
+  { index = "pytorch", marker = "python_version < '3.13'" },
+]
+torchvision = [
+  { index = "pytorch-nightly", marker = "python_version >= '3.13'" },
+  { index = "pytorch", marker = "python_version < '3.13'" },
+]
+
 [build-system]
 requires = ["hatchling"]
 build-backend = "hatchling.build"

src/crewai/__init__.py

@@ -18,7 +18,7 @@ warnings.filterwarnings(
     category=UserWarning,
     module="pydantic.main",
 )
-__version__ = "0.121.0"
+__version__ = "0.121.1"
 __all__ = [
     "Agent",
     "Crew",

src/crewai/cli/plus_api.py

@@ -1,5 +1,5 @@
 from os import getenv
-from typing import Optional
+from typing import List, Optional
 from urllib.parse import urljoin
 
 import requests
@@ -48,6 +48,7 @@ class PlusAPI:
         version: str,
         description: Optional[str],
         encoded_file: str,
+        available_exports: Optional[List[str]] = None,
     ):
         params = {
             "handle": handle,
@@ -55,6 +56,7 @@ class PlusAPI:
             "version": version,
             "file": encoded_file,
             "description": description,
+            "available_exports": available_exports,
         }
         return self._make_request("POST", f"{self.TOOLS_RESOURCE}", json=params)
 

src/crewai/cli/templates/crew/pyproject.toml

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<3.13"
 dependencies = [
-    "crewai[tools]>=0.121.0,<1.0.0"
+    "crewai[tools]>=0.121.1,<1.0.0"
 ]
 
 [project.scripts]

src/crewai/cli/templates/flow/pyproject.toml

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<3.13"
 dependencies = [
-    "crewai[tools]>=0.121.0,<1.0.0",
+    "crewai[tools]>=0.121.1,<1.0.0",
 ]
 
 [project.scripts]

src/crewai/cli/templates/tool/pyproject.toml

@@ -5,7 +5,7 @@ description = "Power up your crews with {{folder_name}}"
 readme = "README.md"
 requires-python = ">=3.10,<3.13"
 dependencies = [
-    "crewai[tools]>=0.121.0"
+    "crewai[tools]>=0.121.1"
 ]
 
 [tool.crewai]

src/crewai/cli/templates/tool/src/{{folder_name}}/__init__.py

@@ -0,0 +1,3 @@
+from .tool import {{class_name}}
+
+__all__ = ["{{class_name}}"]

src/crewai/cli/tools/main.py

@@ -3,6 +3,7 @@ import os
 import subprocess
 import tempfile
 from pathlib import Path
+from typing import Any
 
 import click
 from rich.console import Console
@@ -11,6 +12,7 @@ from crewai.cli import git
 from crewai.cli.command import BaseCommand, PlusAPIMixin
 from crewai.cli.config import Settings
 from crewai.cli.utils import (
+    extract_available_exports,
     get_project_description,
     get_project_name,
     get_project_version,
@@ -82,6 +84,14 @@ class ToolCommand(BaseCommand, PlusAPIMixin):
         project_description = get_project_description(require=False)
         encoded_tarball = None
 
+        console.print("[bold blue]Discovering tools from your project...[/bold blue]")
+        available_exports = extract_available_exports()
+
+        if available_exports:
+            console.print(
+                f"[green]Found these tools to publish: {', '.join(available_exports)}[/green]"
+            )
+
         with tempfile.TemporaryDirectory() as temp_build_dir:
             subprocess.run(
                 ["uv", "build", "--sdist", "--out-dir", temp_build_dir],
@@ -105,12 +115,14 @@ class ToolCommand(BaseCommand, PlusAPIMixin):
 
             encoded_tarball = base64.b64encode(tarball_contents).decode("utf-8")
 
+        console.print("[bold blue]Publishing tool to repository...[/bold blue]")
         publish_response = self.plus_api_client.publish_tool(
             handle=project_name,
             is_public=is_public,
             version=project_version,
             description=project_description,
             encoded_file=f"data:application/x-gzip;base64,{encoded_tarball}",
+            available_exports=available_exports,
         )
 
         self._validate_response(publish_response)
@@ -167,7 +179,8 @@ class ToolCommand(BaseCommand, PlusAPIMixin):
             "Successfully authenticated to the tool repository.", style="bold green"
         )
 
-    def _add_package(self, tool_details):
+    def _add_package(self, tool_details: dict[str, Any]):
+        is_from_pypi = tool_details.get("source", None) == "pypi"
         tool_handle = tool_details["handle"]
         repository_handle = tool_details["repository"]["handle"]
         repository_url = tool_details["repository"]["url"]
@@ -176,10 +189,13 @@ class ToolCommand(BaseCommand, PlusAPIMixin):
         add_package_command = [
             "uv",
             "add",
-            "--index",
-            index,
-            tool_handle,
         ]
+
+        if is_from_pypi:
+            add_package_command.append(tool_handle)
+        else:
+            add_package_command.extend(["--index", index, tool_handle])
+
         add_package_result = subprocess.run(
             add_package_command,
             capture_output=False,

src/crewai/cli/utils.py

@@ -1,8 +1,10 @@
+import importlib.util
 import os
 import shutil
 import sys
 from functools import reduce
-from inspect import isfunction, ismethod
+from inspect import getmro, isclass, isfunction, ismethod
+from pathlib import Path
 from typing import Any, Dict, List, get_type_hints
 
 import click
@@ -339,3 +341,112 @@ def fetch_crews(module_attr) -> list[Crew]:
             if crew_instance := get_crew_instance(attr):
                 crew_instances.append(crew_instance)
     return crew_instances
+
+
+def is_valid_tool(obj):
+    from crewai.tools.base_tool import Tool
+
+    if isclass(obj):
+        try:
+            return any(base.__name__ == "BaseTool" for base in getmro(obj))
+        except (TypeError, AttributeError):
+            return False
+
+    return isinstance(obj, Tool)
+
+
+def extract_available_exports(dir_path: str = "src"):
+    """
+    Extract available tool classes from the project's __init__.py files.
+    Only includes classes that inherit from BaseTool or functions decorated with @tool.
+
+    Returns:
+        list: A list of valid tool class names or ["BaseTool"] if none found
+    """
+    try:
+        init_files = Path(dir_path).glob("**/__init__.py")
+        available_exports = []
+
+        for init_file in init_files:
+            tools = _load_tools_from_init(init_file)
+            available_exports.extend(tools)
+
+        if not available_exports:
+            _print_no_tools_warning()
+            raise SystemExit(1)
+
+        return available_exports
+
+    except Exception as e:
+        console.print(f"[red]Error: Could not extract tool classes: {str(e)}[/red]")
+        console.print(
+            "Please ensure your project contains valid tools (classes inheriting from BaseTool or functions with @tool decorator)."
+        )
+        raise SystemExit(1)
+
+
+def _load_tools_from_init(init_file: Path) -> list[dict[str, Any]]:
+    """
+    Load and validate tools from a given __init__.py file.
+    """
+    spec = importlib.util.spec_from_file_location("temp_module", init_file)
+
+    if not spec or not spec.loader:
+        return []
+
+    module = importlib.util.module_from_spec(spec)
+    sys.modules["temp_module"] = module
+
+    try:
+        spec.loader.exec_module(module)
+
+        if not hasattr(module, "__all__"):
+            console.print(
+                f"[bold yellow]Warning: No __all__ defined in {init_file}[/bold yellow]"
+            )
+            raise SystemExit(1)
+
+        return [
+            {
+                "name": name,
+            }
+            for name in module.__all__
+            if hasattr(module, name) and is_valid_tool(getattr(module, name))
+        ]
+
+    except Exception as e:
+        console.print(f"[red]Warning: Could not load {init_file}: {str(e)}[/red]")
+        raise SystemExit(1)
+
+    finally:
+        sys.modules.pop("temp_module", None)
+
+
+def _print_no_tools_warning():
+    """
+    Display warning and usage instructions if no tools were found.
+    """
+    console.print(
+        "\n[bold yellow]Warning: No valid tools were exposed in your __init__.py file![/bold yellow]"
+    )
+    console.print(
+        "Your __init__.py file must contain all classes that inherit from [bold]BaseTool[/bold] "
+        "or functions decorated with [bold]@tool[/bold]."
+    )
+    console.print(
+        "\nExample:\n[dim]# In your __init__.py file[/dim]\n"
+        "[green]__all__ = ['YourTool', 'your_tool_function'][/green]\n\n"
+        "[dim]# In your tool.py file[/dim]\n"
+        "[green]from crewai.tools import BaseTool, tool\n\n"
+        "# Tool class example\n"
+        "class YourTool(BaseTool):\n"
+        '    name = "your_tool"\n'
+        '    description = "Your tool description"\n'
+        "    # ... rest of implementation\n\n"
+        "# Decorated function example\n"
+        "@tool\n"
+        "def your_tool_function(text: str) -> str:\n"
+        '    """Your tool description"""\n'
+        "    # ... implementation\n"
+        "    return result\n"
+    )

src/crewai/knowledge/embedder/fastembed.py

@@ -1,93 +0,0 @@
-from pathlib import Path
-from typing import List, Optional, Union
-
-import numpy as np
-
-from .base_embedder import BaseEmbedder
-
-try:
-    from fastembed_gpu import TextEmbedding  # type: ignore
-
-    FASTEMBED_AVAILABLE = True
-except ImportError:
-    try:
-        from fastembed import TextEmbedding
-
-        FASTEMBED_AVAILABLE = True
-    except ImportError:
-        FASTEMBED_AVAILABLE = False
-
-
-class FastEmbed(BaseEmbedder):
-    """
-    A wrapper class for text embedding models using FastEmbed
-    """
-
-    def __init__(
-        self,
-        model_name: str = "BAAI/bge-small-en-v1.5",
-        cache_dir: Optional[Union[str, Path]] = None,
-    ):
-        """
-        Initialize the embedding model
-
-        Args:
-            model_name: Name of the model to use
-            cache_dir: Directory to cache the model
-            gpu: Whether to use GPU acceleration
-        """
-        if not FASTEMBED_AVAILABLE:
-            raise ImportError(
-                "FastEmbed is not installed. Please install it with: "
-                "uv pip install fastembed or uv pip install fastembed-gpu for GPU support"
-            )
-
-        self.model = TextEmbedding(
-            model_name=model_name,
-            cache_dir=str(cache_dir) if cache_dir else None,
-        )
-
-    def embed_chunks(self, chunks: List[str]) -> List[np.ndarray]:
-        """
-        Generate embeddings for a list of text chunks
-
-        Args:
-            chunks: List of text chunks to embed
-
-        Returns:
-            List of embeddings
-        """
-        embeddings = list(self.model.embed(chunks))
-        return embeddings
-
-    def embed_texts(self, texts: List[str]) -> List[np.ndarray]:
-        """
-        Generate embeddings for a list of texts
-
-        Args:
-            texts: List of texts to embed
-
-        Returns:
-            List of embeddings
-        """
-        embeddings = list(self.model.embed(texts))
-        return embeddings
-
-    def embed_text(self, text: str) -> np.ndarray:
-        """
-        Generate embedding for a single text
-
-        Args:
-            text: Text to embed
-
-        Returns:
-            Embedding array
-        """
-        return self.embed_texts([text])[0]
-
-    @property
-    def dimension(self) -> int:
-        """Get the dimension of the embeddings"""
-        # Generate a test embedding to get dimensions
-        test_embed = self.embed_text("test")
-        return len(test_embed)

src/crewai/llm.py

@@ -5,7 +5,7 @@ import sys
 import threading
 import warnings
 from collections import defaultdict
-from contextlib import contextmanager, redirect_stderr, redirect_stdout
+from contextlib import contextmanager
 from typing import (
     Any,
     DefaultDict,
@@ -18,7 +18,7 @@ from typing import (
     Union,
     cast,
 )
-
+from datetime import datetime
 from dotenv import load_dotenv
 from litellm.types.utils import ChatCompletionDeltaToolCall
 from pydantic import BaseModel, Field
@@ -30,6 +30,11 @@ from crewai.utilities.events.llm_events import (
     LLMCallType,
     LLMStreamChunkEvent,
 )
+from crewai.utilities.events.tool_usage_events import (
+    ToolUsageStartedEvent,
+    ToolUsageFinishedEvent,
+    ToolUsageErrorEvent,
+)
 
 with warnings.catch_warnings():
     warnings.simplefilter("ignore", UserWarning)
@@ -244,6 +249,30 @@ LLM_CONTEXT_WINDOW_SIZES = {
     "mistral/mistral-large-latest": 32768,
     "mistral/mistral-large-2407": 32768,
     "mistral/mistral-large-2402": 32768,
+    "openai/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": 131072,
+    "openai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": 131072,
+    "openai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": 131072,
+    "openai/meta-llama/Meta-Llama-3.2-90B-Vision-Instruct-Turbo": 131072,
+    "openai/meta-llama/Meta-Llama-3.2-11B-Vision-Instruct-Turbo": 131072,
+    "openai/meta-llama/Meta-Llama-3.2-3B-Instruct-Turbo": 131072,
+    "openai/meta-llama/Meta-Llama-3.2-1B-Instruct-Turbo": 131072,
+    "openai/anthropic/claude-3-5-sonnet-20241022": 200000,
+    "openai/anthropic/claude-3-5-haiku-20241022": 200000,
+    "openai/anthropic/claude-3-opus-20240229": 200000,
+    "openai/anthropic/claude-3-sonnet-20240229": 200000,
+    "openai/anthropic/claude-3-haiku-20240307": 200000,
+    "openai/mistralai/Mistral-7B-Instruct-v0.3": 32768,
+    "openai/mistralai/Mixtral-8x7B-Instruct-v0.1": 32768,
+    "openai/mistralai/Mixtral-8x22B-Instruct-v0.1": 65536,
+    "openai/google/gemma-2-9b-it": 8192,
+    "openai/google/gemma-2-27b-it": 8192,
+    "openai/Qwen/Qwen2.5-72B-Instruct-Turbo": 131072,
+    "openai/Qwen/Qwen2.5-32B-Instruct-Turbo": 131072,
+    "openai/Qwen/Qwen2.5-14B-Instruct-Turbo": 131072,
+    "openai/Qwen/Qwen2.5-7B-Instruct-Turbo": 131072,
+    "openai/deepseek-ai/DeepSeek-V2.5": 131072,
+    "openai/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": 131072,
+    "openai/microsoft/WizardLM-2-8x22B": 65536,
 }
 
 DEFAULT_CONTEXT_WINDOW_SIZE = 8192
@@ -833,7 +862,26 @@ class LLM(BaseLLM):
                 fn = available_functions[function_name]
 
                 # --- 3.2) Execute function
+                assert hasattr(crewai_event_bus, "emit")
+                started_at = datetime.now()
+                crewai_event_bus.emit(
+                    self,
+                    event=ToolUsageStartedEvent(
+                        tool_name=function_name,
+                        tool_args=function_args,
+                    ),
+                )
                 result = fn(**function_args)
+                crewai_event_bus.emit(
+                    self,
+                    event=ToolUsageFinishedEvent(
+                        output=result,
+                        tool_name=function_name,
+                        tool_args=function_args,
+                        started_at=started_at,
+                        finished_at=datetime.now(),
+                    ),
+                )
 
                 # --- 3.3) Emit success event
                 self._handle_emit_call_events(result, LLMCallType.TOOL_CALL)
@@ -849,6 +897,14 @@ class LLM(BaseLLM):
                     self,
                     event=LLMCallFailedEvent(error=f"Tool execution error: {str(e)}"),
                 )
+                crewai_event_bus.emit(
+                    self,
+                    event=ToolUsageErrorEvent(
+                        tool_name=function_name,
+                        tool_args=function_args,
+                        error=f"Tool execution error: {str(e)}"
+                    ),
+                )
         return None
 
     def call(
@@ -1063,7 +1119,7 @@ class LLM(BaseLLM):
 
     def get_context_window_size(self) -> int:
         """
-        Returns the context window size, using 75% of the maximum to avoid
+        Returns the context window size, using 85% of the maximum to avoid
         cutting off messages mid-thread.
 
         Raises:
@@ -1074,6 +1130,7 @@ class LLM(BaseLLM):
 
         MIN_CONTEXT = 1024
         MAX_CONTEXT = 2097152  # Current max from gemini-1.5-pro
+        MAX_SAFE_CONTEXT = 100000  # Warn for very large context windows
 
         # Validate all context window sizes
         for key, value in LLM_CONTEXT_WINDOW_SIZES.items():
@@ -1088,6 +1145,9 @@ class LLM(BaseLLM):
         for key, value in LLM_CONTEXT_WINDOW_SIZES.items():
             if self.model.startswith(key):
                 self.context_window_size = int(value * CONTEXT_WINDOW_USAGE_RATIO)
+                if value > MAX_SAFE_CONTEXT:
+                    import warnings
+                    warnings.warn(f"Model {self.model} uses large context window ({value}). Monitor memory usage.")
         return self.context_window_size
 
     def set_callbacks(self, callbacks: List[Any]):

src/crewai/tools/__init__.py

@@ -1 +1,7 @@
-from .base_tool import BaseTool, tool
+from .base_tool import BaseTool, tool, EnvVar
+
+__all__ = [
+    "BaseTool",
+    "tool",
+    "EnvVar",
+]

src/crewai/tools/base_tool.py

@@ -1,7 +1,7 @@
 import asyncio
 from abc import ABC, abstractmethod
 from inspect import signature
-from typing import Any, Callable, Type, get_args, get_origin
+from typing import Any, Callable, Type, get_args, get_origin, Optional, List
 
 from pydantic import (
     BaseModel,
@@ -14,6 +14,11 @@ from pydantic import BaseModel as PydanticBaseModel
 
 from crewai.tools.structured_tool import CrewStructuredTool
 
+class EnvVar(BaseModel):
+    name: str
+    description: str
+    required: bool = True
+    default: Optional[str] = None
 
 class BaseTool(BaseModel, ABC):
     class _ArgsSchemaPlaceholder(PydanticBaseModel):
@@ -25,6 +30,8 @@ class BaseTool(BaseModel, ABC):
     """The unique name of the tool that clearly communicates its purpose."""
     description: str
     """Used to tell the model how/when/why to use the tool."""
+    env_vars: List[EnvVar] = []
+    """List of environment variables used by the tool."""
     args_schema: Type[PydanticBaseModel] = Field(
         default_factory=_ArgsSchemaPlaceholder, validate_default=True
     )

src/crewai/utilities/events/event_listener.py

@@ -2,7 +2,7 @@ from io import StringIO
 from typing import Any, Dict
 
 from pydantic import Field, PrivateAttr
-
+from crewai.llm import LLM
 from crewai.task import Task
 from crewai.telemetry.telemetry import Telemetry
 from crewai.utilities import Logger
@@ -283,27 +283,43 @@ class EventListener(BaseEventListener):
 
         @crewai_event_bus.on(ToolUsageStartedEvent)
         def on_tool_usage_started(source, event: ToolUsageStartedEvent):
-            self.formatter.handle_tool_usage_started(
-                self.formatter.current_agent_branch,
-                event.tool_name,
+            if isinstance(source, LLM):
+                self.formatter.handle_llm_tool_usage_started(
+                    event.tool_name,
+                )
+            else:
+                self.formatter.handle_tool_usage_started(
+                    self.formatter.current_agent_branch,
+                    event.tool_name,
                 self.formatter.current_crew_tree,
             )
 
         @crewai_event_bus.on(ToolUsageFinishedEvent)
         def on_tool_usage_finished(source, event: ToolUsageFinishedEvent):
-            self.formatter.handle_tool_usage_finished(
-                self.formatter.current_tool_branch,
-                event.tool_name,
-                self.formatter.current_crew_tree,
-            )
+            if isinstance(source, LLM):
+                self.formatter.handle_llm_tool_usage_finished(
+                    event.tool_name,
+                )
+            else:
+                self.formatter.handle_tool_usage_finished(
+                    self.formatter.current_tool_branch,
+                    event.tool_name,
+                    self.formatter.current_crew_tree,
+                )
 
         @crewai_event_bus.on(ToolUsageErrorEvent)
         def on_tool_usage_error(source, event: ToolUsageErrorEvent):
-            self.formatter.handle_tool_usage_error(
-                self.formatter.current_tool_branch,
-                event.tool_name,
-                event.error,
-                self.formatter.current_crew_tree,
+            if isinstance(source, LLM):
+                self.formatter.handle_llm_tool_usage_error(
+                    event.tool_name,
+                    event.error,
+                )
+            else:
+                self.formatter.handle_tool_usage_error(
+                    self.formatter.current_tool_branch,
+                    event.tool_name,
+                    event.error,
+                    self.formatter.current_crew_tree,
             )
 
         # ----------- LLM EVENTS -----------

src/crewai/utilities/events/tool_usage_events.py

@@ -7,11 +7,11 @@ from .base_events import BaseEvent
 class ToolUsageEvent(BaseEvent):
     """Base event for tool usage tracking"""
 
-    agent_key: str
-    agent_role: str
+    agent_key: Optional[str] = None
+    agent_role: Optional[str] = None
     tool_name: str
     tool_args: Dict[str, Any] | str
-    tool_class: str
+    tool_class: Optional[str] = None
     run_attempts: int | None = None
     delegations: int | None = None
     agent: Optional[Any] = None

src/crewai/utilities/events/utils/console_formatter.py

@@ -17,6 +17,7 @@ class ConsoleFormatter:
     current_lite_agent_branch: Optional[Tree] = None
     tool_usage_counts: Dict[str, int] = {}
     current_reasoning_branch: Optional[Tree] = None  # Track reasoning status
+    current_llm_tool_tree: Optional[Tree] = None
 
     def __init__(self, verbose: bool = False):
         self.console = Console(width=None)
@@ -426,6 +427,51 @@ class ConsoleFormatter:
         self.print()
         return method_branch
 
+    def get_llm_tree(self, tool_name: str):
+        text = Text()
+        text.append(f"🔧 Using {tool_name} from LLM available_function", style="yellow")
+
+        tree = self.current_flow_tree or self.current_crew_tree
+
+        if tree:
+            tree.add(text)
+
+        return tree or Tree(text)
+
+    def handle_llm_tool_usage_started(
+        self,
+        tool_name: str,
+    ):
+        tree = self.get_llm_tree(tool_name)
+        self.add_tree_node(tree, "🔄 Tool Usage Started", "green")
+        self.print(tree)
+        self.print()
+        return tree
+
+    def handle_llm_tool_usage_finished(
+        self,
+        tool_name: str,
+    ):
+        tree = self.get_llm_tree(tool_name)
+        self.add_tree_node(tree, "✅ Tool Usage Completed", "green")
+        self.print(tree)
+        self.print()
+
+    def handle_llm_tool_usage_error(
+        self,
+        tool_name: str,
+        error: str,
+    ):
+        tree = self.get_llm_tree(tool_name)
+        self.add_tree_node(tree, "❌ Tool Usage Failed", "red")
+        self.print(tree)
+        self.print()
+
+        error_content = self.create_status_content(
+            "Tool Usage Failed", tool_name, "red", Error=error
+        )
+        self.print_panel(error_content, "Tool Error", "red")
+
     def handle_tool_usage_started(
         self,
         agent_branch: Optional[Tree],

tests/cassettes/test_handle_streaming_tool_calls_with_error.yaml

@@ -0,0 +1,143 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "What is the weather in New York?"}],
+      "model": "gpt-4o", "stop": [], "stream": true, "stream_options": {"include_usage":
+      true}, "tools": [{"type": "function", "function": {"name": "get_weather", "description":
+      "Get the current weather in a given location", "parameters": {"type": "object",
+      "properties": {"location": {"type": "string", "description": "The city and state,
+      e.g. San Francisco, CA"}}, "required": ["location"]}}}]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '470'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=3UeEmz_rnmsoZxrVUv32u35gJOi766GDWNe5_RTjiPk-1736537376739-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: 'data: {"id":"chatcmpl-BcY6NFDeu4HFOAIarpwSNAUEMuPTg","object":"chat.completion.chunk","created":1748527251,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_07871e2ad8","choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_UkMsNK0RTJ1nlT19WqgLJYV9","type":"function","function":{"name":"get_weather","arguments":""}}],"refusal":null},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BcY6NFDeu4HFOAIarpwSNAUEMuPTg","object":"chat.completion.chunk","created":1748527251,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_07871e2ad8","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BcY6NFDeu4HFOAIarpwSNAUEMuPTg","object":"chat.completion.chunk","created":1748527251,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_07871e2ad8","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"location"}}]},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BcY6NFDeu4HFOAIarpwSNAUEMuPTg","object":"chat.completion.chunk","created":1748527251,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_07871e2ad8","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BcY6NFDeu4HFOAIarpwSNAUEMuPTg","object":"chat.completion.chunk","created":1748527251,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_07871e2ad8","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"New"}}]},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BcY6NFDeu4HFOAIarpwSNAUEMuPTg","object":"chat.completion.chunk","created":1748527251,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_07871e2ad8","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"
+        York"}}]},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BcY6NFDeu4HFOAIarpwSNAUEMuPTg","object":"chat.completion.chunk","created":1748527251,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_07871e2ad8","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":","}}]},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BcY6NFDeu4HFOAIarpwSNAUEMuPTg","object":"chat.completion.chunk","created":1748527251,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_07871e2ad8","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"
+        NY"}}]},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BcY6NFDeu4HFOAIarpwSNAUEMuPTg","object":"chat.completion.chunk","created":1748527251,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_07871e2ad8","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BcY6NFDeu4HFOAIarpwSNAUEMuPTg","object":"chat.completion.chunk","created":1748527251,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_07871e2ad8","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"tool_calls"}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BcY6NFDeu4HFOAIarpwSNAUEMuPTg","object":"chat.completion.chunk","created":1748527251,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_07871e2ad8","choices":[],"usage":{"prompt_tokens":68,"completion_tokens":17,"total_tokens":85,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}}}
+
+
+        data: [DONE]
+
+
+        '
+    headers:
+      CF-RAY:
+      - 947685373af8a435-GRU
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Thu, 29 May 2025 14:00:51 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=fFoq7oCHLgmljA4hsHWxTGHMEWJ.0t1XTuDptZPPkOc-1748527251-1.0.1.1-PP3Hd7XzA4AQFn0JQWjuQdhFwey0Pj9maUWKfFG16Bkl69Uk65A8XKN73UbsvO327TruwxameKb_m_HDePCR.YN0TZlE8Pu45WsA9shDwKY;
+        path=/; expires=Thu, 29-May-25 14:30:51 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=ut1CVX5GOYnv03fiV2Dsv7cm5soJmwgSutkPAEuVXWg-1748527251565-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '332'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-envoy-upstream-service-time:
+      - '334'
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29999989'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_1dc91fc964a8d23ee023693400e5c181
+    status:
+      code: 200
+      message: OK
+version: 1

tests/cassettes/test_llm_callback_replacement.yaml

@@ -202,4 +202,63 @@ interactions:
       - req_366bcd7dfe94e2a2b5640fd9bb1c5a6b
     http_version: HTTP/1.1
     status_code: 200
+- request:
+    body: !!binary |
+      CtcMCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSrgwKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKUCAoQu3w5ZNCcMWutYN9ACENEihIIIWUtKzKLQXoqDENyZXcgQ3JlYXRlZDABOcjc
+      jv4SBEQYQWg/lv4SBEQYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTIwLjFKGgoOcHl0aG9uX3Zl
+      cnNpb24SCAoGMy4xMi45Si4KCGNyZXdfa2V5EiIKIDY5NDY1NGEzMThmNzE5ODgzYzA2ZjhlNmQ5
+      YTc1NDlmSjEKB2NyZXdfaWQSJgokMjI4NzU3NTAtYjIwMC00MTI4LWJmYjUtYTFmNTFjNDhlNDk5
+      ShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3
+      X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUo6ChBjcmV3
+      X2ZpbmdlcnByaW50EiYKJDBhZGQxM2U2LTBhYWQtNDUyNS1iYTE0LWZhMDUzZGM2ZjE0ZUo7Chtj
+      cmV3X2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoaMjAyNS0wNS0yOVQxMDo1NzoxNC45NTE4MTlK
+      zAIKC2NyZXdfYWdlbnRzErwCCrkCW3sia2V5IjogIjU1ODY5YmNiMTYzMjNlNzEyOWQyNTIzNjJj
+      ODU1ZGE2IiwgImlkIjogIjJiY2UyZTE0LWIyN2UtNDM1MC1iZmIyLWE1YTNkMTRmYTJhMCIsICJy
+      b2xlIjogIlNheSBIaSIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyNSwgIm1heF9y
+      cG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJ0ZXN0LW1vZGVs
+      IiwgImRlbGVnYXRpb25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6
+      IGZhbHNlLCAibWF4X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVzIjogW119XUr7AQoKY3Jl
+      d190YXNrcxLsAQrpAVt7ImtleSI6ICJkZTI5NDBmMDZhZDhhNDE2YzI4Y2MwZjI2MTBmMTgwYiIs
+      ICJpZCI6ICJiM2MyMzNkZC1kNDk2LTQ1YjQtYWFkMy1kYzYyZGI3ZjJiZWEiLCAiYXN5bmNfZXhl
+      Y3V0aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogIlNh
+      eSBIaSIsICJhZ2VudF9rZXkiOiAiNTU4NjliY2IxNjMyM2U3MTI5ZDI1MjM2MmM4NTVkYTYiLCAi
+      dG9vbHNfbmFtZXMiOiBbXX1degIYAYUBAAEAABKABAoQaW1V2ASOUN5hjxpKH5WT+BIIe6lsRrYF
+      84MqDFRhc2sgQ3JlYXRlZDABOfA/rv4SBEQYQSC1rv4SBEQYSi4KCGNyZXdfa2V5EiIKIDY5NDY1
+      NGEzMThmNzE5ODgzYzA2ZjhlNmQ5YTc1NDlmSjEKB2NyZXdfaWQSJgokMjI4NzU3NTAtYjIwMC00
+      MTI4LWJmYjUtYTFmNTFjNDhlNDk5Si4KCHRhc2tfa2V5EiIKIGRlMjk0MGYwNmFkOGE0MTZjMjhj
+      YzBmMjYxMGYxODBiSjEKB3Rhc2tfaWQSJgokYjNjMjMzZGQtZDQ5Ni00NWI0LWFhZDMtZGM2MmRi
+      N2YyYmVhSjoKEGNyZXdfZmluZ2VycHJpbnQSJgokMGFkZDEzZTYtMGFhZC00NTI1LWJhMTQtZmEw
+      NTNkYzZmMTRlSjoKEHRhc2tfZmluZ2VycHJpbnQSJgokZGVlNDA1YjgtMTkxNC00N2NkLTlkMTgt
+      ZTdmZDA0NjFkOGE4SjsKG3Rhc2tfZmluZ2VycHJpbnRfY3JlYXRlZF9hdBIcChoyMDI1LTA1LTI5
+      VDEwOjU3OjE0Ljk1MTc4M0o7ChFhZ2VudF9maW5nZXJwcmludBImCiRiNWQ0NGNlMS00NGRjLTQ0
+      YzYtYTU1YS0xODZhM2QxZmU2YjJ6AhgBhQEAAQAA
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '1626'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.31.1
+    method: POST
+    uri: https://telemetry.crewai.com:4319/v1/traces
+  response:
+    body:
+      string: "\n\0"
+    headers:
+      Content-Length:
+      - '2'
+      Content-Type:
+      - application/x-protobuf
+      Date:
+      - Thu, 29 May 2025 13:57:17 GMT
+    status:
+      code: 200
+      message: OK
 version: 1

tests/cli/test_plus_api.py

@@ -61,6 +61,7 @@ class TestPlusAPI(unittest.TestCase):
             "version": version,
             "file": encoded_file,
             "description": description,
+            "available_exports": None,
         }
         mock_make_request.assert_called_once_with(
             "POST", "/crewai_plus/api/v1/tools", json=params
@@ -87,6 +88,7 @@ class TestPlusAPI(unittest.TestCase):
             "version": version,
             "file": encoded_file,
             "description": description,
+            "available_exports": None,
         }
         mock_make_request.assert_called_once_with(
             "POST", "/crewai_plus/api/v1/tools", json=params

tests/cli/test_utils.py

@@ -1,6 +1,7 @@
 import os
 import shutil
 import tempfile
+from pathlib import Path
 
 import pytest
 
@@ -100,3 +101,163 @@ def test_tree_copy_to_existing_directory(temp_tree):
         assert os.path.isfile(os.path.join(dest_dir, "file1.txt"))
     finally:
         shutil.rmtree(dest_dir)
+
+
+@pytest.fixture
+def temp_project_dir():
+    """Create a temporary directory for testing tool extraction."""
+    with tempfile.TemporaryDirectory() as temp_dir:
+        yield Path(temp_dir)
+
+
+def create_init_file(directory, content):
+    return create_file(directory / "__init__.py", content)
+
+
+def test_extract_available_exports_empty_project(temp_project_dir, capsys):
+    with pytest.raises(SystemExit):
+        utils.extract_available_exports(dir_path=temp_project_dir)
+    captured = capsys.readouterr()
+
+    assert "No valid tools were exposed in your __init__.py file" in captured.out
+
+
+def test_extract_available_exports_no_init_file(temp_project_dir, capsys):
+    (temp_project_dir / "some_file.py").write_text("print('hello')")
+    with pytest.raises(SystemExit):
+        utils.extract_available_exports(dir_path=temp_project_dir)
+    captured = capsys.readouterr()
+
+    assert "No valid tools were exposed in your __init__.py file" in captured.out
+
+
+def test_extract_available_exports_empty_init_file(temp_project_dir, capsys):
+    create_init_file(temp_project_dir, "")
+    with pytest.raises(SystemExit):
+        utils.extract_available_exports(dir_path=temp_project_dir)
+    captured = capsys.readouterr()
+
+    assert "Warning: No __all__ defined in" in captured.out
+
+
+def test_extract_available_exports_no_all_variable(temp_project_dir, capsys):
+    create_init_file(
+        temp_project_dir,
+        "from crewai.tools import BaseTool\n\nclass MyTool(BaseTool):\n    pass",
+    )
+    with pytest.raises(SystemExit):
+        utils.extract_available_exports(dir_path=temp_project_dir)
+    captured = capsys.readouterr()
+
+    assert "Warning: No __all__ defined in" in captured.out
+
+
+def test_extract_available_exports_valid_base_tool_class(temp_project_dir):
+    create_init_file(
+        temp_project_dir,
+        """from crewai.tools import BaseTool
+
+class MyTool(BaseTool):
+    name: str = "my_tool"
+    description: str = "A test tool"
+
+__all__ = ['MyTool']
+""",
+    )
+    tools = utils.extract_available_exports(dir_path=temp_project_dir)
+    assert [{"name": "MyTool"}] == tools
+
+
+def test_extract_available_exports_valid_tool_decorator(temp_project_dir):
+    create_init_file(
+        temp_project_dir,
+        """from crewai.tools import tool
+
+@tool
+def my_tool_function(text: str) -> str:
+    \"\"\"A test tool function\"\"\"
+    return text
+
+__all__ = ['my_tool_function']
+""",
+    )
+    tools = utils.extract_available_exports(dir_path=temp_project_dir)
+    assert [{"name": "my_tool_function"}] == tools
+
+
+def test_extract_available_exports_multiple_valid_tools(temp_project_dir):
+    create_init_file(
+        temp_project_dir,
+        """from crewai.tools import BaseTool, tool
+
+class MyTool(BaseTool):
+    name: str = "my_tool"
+    description: str = "A test tool"
+
+@tool
+def my_tool_function(text: str) -> str:
+    \"\"\"A test tool function\"\"\"
+    return text
+
+__all__ = ['MyTool', 'my_tool_function']
+""",
+    )
+    tools = utils.extract_available_exports(dir_path=temp_project_dir)
+    assert [{"name": "MyTool"}, {"name": "my_tool_function"}] == tools
+
+
+def test_extract_available_exports_with_invalid_tool_decorator(temp_project_dir):
+    create_init_file(
+        temp_project_dir,
+        """from crewai.tools import BaseTool
+
+class MyTool(BaseTool):
+    name: str = "my_tool"
+    description: str = "A test tool"
+
+def not_a_tool():
+    pass
+
+__all__ = ['MyTool', 'not_a_tool']
+""",
+    )
+    tools = utils.extract_available_exports(dir_path=temp_project_dir)
+    assert [{"name": "MyTool"}] == tools
+
+
+def test_extract_available_exports_import_error(temp_project_dir, capsys):
+    create_init_file(
+        temp_project_dir,
+        """from nonexistent_module import something
+
+class MyTool(BaseTool):
+    pass
+
+__all__ = ['MyTool']
+""",
+    )
+    with pytest.raises(SystemExit):
+        utils.extract_available_exports(dir_path=temp_project_dir)
+    captured = capsys.readouterr()
+
+    assert "nonexistent_module" in captured.out
+
+
+def test_extract_available_exports_syntax_error(temp_project_dir, capsys):
+    create_init_file(
+        temp_project_dir,
+        """from crewai.tools import BaseTool
+
+class MyTool(BaseTool):
+    # Missing closing parenthesis
+    def __init__(self, name:
+        pass
+
+__all__ = ['MyTool']
+""",
+    )
+    with pytest.raises(SystemExit):
+        utils.extract_available_exports(dir_path=temp_project_dir)
+    captured = capsys.readouterr()
+
+    assert "was never closed" in captured.out

tests/cli/tools/test_main.py

@@ -85,6 +85,36 @@ def test_install_success(mock_get, mock_subprocess_run, capsys, tool_command):
         env=unittest.mock.ANY,
     )
 
+@patch("crewai.cli.tools.main.subprocess.run")
+@patch("crewai.cli.plus_api.PlusAPI.get_tool")
+def test_install_success_from_pypi(mock_get, mock_subprocess_run, capsys, tool_command):
+    mock_get_response = MagicMock()
+    mock_get_response.status_code = 200
+    mock_get_response.json.return_value = {
+        "handle": "sample-tool",
+        "repository": {"handle": "sample-repo", "url": "https://example.com/repo"},
+        "source": "pypi",
+    }
+    mock_get.return_value = mock_get_response
+    mock_subprocess_run.return_value = MagicMock(stderr=None)
+
+    tool_command.install("sample-tool")
+    output = capsys.readouterr().out
+    assert "Successfully installed sample-tool" in output
+
+    mock_get.assert_has_calls([mock.call("sample-tool"), mock.call().json()])
+    mock_subprocess_run.assert_any_call(
+        [
+            "uv",
+            "add",
+            "sample-tool",
+        ],
+        capture_output=False,
+        text=True,
+        check=True,
+        env=unittest.mock.ANY,
+    )
+
 
 @patch("crewai.cli.plus_api.PlusAPI.get_tool")
 def test_install_tool_not_found(mock_get, capsys, tool_command):
@@ -135,7 +165,9 @@ def test_publish_when_not_in_sync(mock_is_synced, capsys, tool_command):
 )
 @patch("crewai.cli.plus_api.PlusAPI.publish_tool")
 @patch("crewai.cli.tools.main.git.Repository.is_synced", return_value=False)
+@patch("crewai.cli.tools.main.extract_available_exports", return_value=["SampleTool"])
 def test_publish_when_not_in_sync_and_force(
+    mock_available_exports,
     mock_is_synced,
     mock_publish,
     mock_open,
@@ -168,6 +200,7 @@ def test_publish_when_not_in_sync_and_force(
         version="1.0.0",
         description="A sample tool",
         encoded_file=unittest.mock.ANY,
+        available_exports=["SampleTool"],
     )
 
 
@@ -183,7 +216,9 @@ def test_publish_when_not_in_sync_and_force(
 )
 @patch("crewai.cli.plus_api.PlusAPI.publish_tool")
 @patch("crewai.cli.tools.main.git.Repository.is_synced", return_value=True)
+@patch("crewai.cli.tools.main.extract_available_exports", return_value=["SampleTool"])
 def test_publish_success(
+    mock_available_exports,
     mock_is_synced,
     mock_publish,
     mock_open,
@@ -216,6 +251,7 @@ def test_publish_success(
         version="1.0.0",
         description="A sample tool",
         encoded_file=unittest.mock.ANY,
+        available_exports=["SampleTool"],
     )
 
 
@@ -230,7 +266,9 @@ def test_publish_success(
     read_data=b"sample tarball content",
 )
 @patch("crewai.cli.plus_api.PlusAPI.publish_tool")
+@patch("crewai.cli.tools.main.extract_available_exports", return_value=["SampleTool"])
 def test_publish_failure(
+    mock_available_exports,
     mock_publish,
     mock_open,
     mock_listdir,
@@ -266,7 +304,9 @@ def test_publish_failure(
     read_data=b"sample tarball content",
 )
 @patch("crewai.cli.plus_api.PlusAPI.publish_tool")
+@patch("crewai.cli.tools.main.extract_available_exports", return_value=["SampleTool"])
 def test_publish_api_error(
+    mock_available_exports,
     mock_publish,
     mock_open,
     mock_listdir,

tests/llm_test.py

@@ -2,7 +2,6 @@ import os
 from time import sleep
 from unittest.mock import MagicMock, patch
 
-import litellm
 import pytest
 from pydantic import BaseModel
 
@@ -11,7 +10,11 @@ from crewai.llm import CONTEXT_WINDOW_USAGE_RATIO, LLM
 from crewai.utilities.events import (
     LLMCallCompletedEvent,
     LLMStreamChunkEvent,
+    ToolUsageStartedEvent,
+    ToolUsageFinishedEvent,
+    ToolUsageErrorEvent,
 )
+
 from crewai.utilities.token_counter_callback import TokenCalcHandler
 
 
@@ -222,7 +225,7 @@ def test_get_custom_llm_provider_gemini():
 
 def test_get_custom_llm_provider_openai():
     llm = LLM(model="gpt-4")
-    assert llm._get_custom_llm_provider() == None
+    assert llm._get_custom_llm_provider() is None
 
 
 def test_validate_call_params_supported():
@@ -511,12 +514,18 @@ def assert_event_count(
     expected_completed_tool_call: int = 0,
     expected_stream_chunk: int = 0,
     expected_completed_llm_call: int = 0,
+    expected_tool_usage_started: int = 0,
+    expected_tool_usage_finished: int = 0,
+    expected_tool_usage_error: int = 0,
     expected_final_chunk_result: str = "",
 ):
     event_count = {
         "completed_tool_call": 0,
         "stream_chunk": 0,
         "completed_llm_call": 0,
+        "tool_usage_started": 0,
+        "tool_usage_finished": 0,
+        "tool_usage_error": 0,
     }
     final_chunk_result = ""
     for _call in mock_emit.call_args_list:
@@ -535,12 +544,21 @@ def assert_event_count(
             and event.call_type.value == "llm_call"
         ):
             event_count["completed_llm_call"] += 1
+        elif isinstance(event, ToolUsageStartedEvent):
+            event_count["tool_usage_started"] += 1
+        elif isinstance(event, ToolUsageFinishedEvent):
+            event_count["tool_usage_finished"] += 1
+        elif isinstance(event, ToolUsageErrorEvent):
+            event_count["tool_usage_error"] += 1
         else:
             continue
 
     assert event_count["completed_tool_call"] == expected_completed_tool_call
     assert event_count["stream_chunk"] == expected_stream_chunk
     assert event_count["completed_llm_call"] == expected_completed_llm_call
+    assert event_count["tool_usage_started"] == expected_tool_usage_started
+    assert event_count["tool_usage_finished"] == expected_tool_usage_finished
+    assert event_count["tool_usage_error"] == expected_tool_usage_error
     assert final_chunk_result == expected_final_chunk_result
 
 
@@ -574,6 +592,34 @@ def test_handle_streaming_tool_calls(get_weather_tool_schema, mock_emit):
         expected_completed_tool_call=1,
         expected_stream_chunk=10,
         expected_completed_llm_call=1,
+        expected_tool_usage_started=1,
+        expected_tool_usage_finished=1,
+        expected_final_chunk_result=expected_final_chunk_result,
+    )
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_handle_streaming_tool_calls_with_error(get_weather_tool_schema, mock_emit):
+    def get_weather_error(location):
+        raise Exception("Error")
+        
+    llm = LLM(model="openai/gpt-4o", stream=True)
+    response = llm.call(
+        messages=[
+            {"role": "user", "content": "What is the weather in New York?"},
+        ],
+        tools=[get_weather_tool_schema],
+        available_functions={
+            "get_weather": get_weather_error
+        },
+    )
+    assert response == ""
+    expected_final_chunk_result = '{"location":"New York, NY"}'
+    assert_event_count(
+        mock_emit=mock_emit,
+        expected_stream_chunk=9,
+        expected_completed_llm_call=1,
+        expected_tool_usage_started=1,
+        expected_tool_usage_error=1,    
         expected_final_chunk_result=expected_final_chunk_result,
     )
 

tests/test_aiml_api_integration.py

@@ -0,0 +1,163 @@
+"""Tests for AI/ML API integration with CrewAI."""
+
+from unittest.mock import patch
+
+from crewai.llm import LLM
+from crewai.utilities.llm_utils import create_llm
+
+
+class TestAIMLAPIIntegration:
+    """Test suite for AI/ML API provider integration."""
+
+    def test_aiml_api_model_context_windows(self):
+        """Test that AI/ML API models have correct context window sizes."""
+        test_cases = [
+            ("openai/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo", 131072),
+            ("openai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo", 131072),
+            ("openai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo", 131072),
+            ("openai/anthropic/claude-3-5-sonnet-20241022", 200000),
+            ("openai/anthropic/claude-3-5-haiku-20241022", 200000),
+            ("openai/mistralai/Mistral-7B-Instruct-v0.3", 32768),
+            ("openai/Qwen/Qwen2.5-72B-Instruct-Turbo", 131072),
+            ("openai/deepseek-ai/DeepSeek-V2.5", 131072),
+        ]
+        
+        for model_name, expected_context_size in test_cases:
+            llm = LLM(model=model_name)
+            expected_usable_size = int(expected_context_size * 0.85)
+            actual_context_size = llm.get_context_window_size()
+            assert actual_context_size == expected_usable_size, (
+                f"Model {model_name} should have context window size {expected_usable_size}, "
+                f"but got {actual_context_size}"
+            )
+
+    def test_aiml_api_provider_detection(self):
+        """Test that AI/ML API models are correctly identified as openai provider."""
+        llm = LLM(model="openai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo")
+        provider = llm._get_custom_llm_provider()
+        assert provider == "openai", f"Expected provider 'openai', but got '{provider}'"
+
+    def test_aiml_api_model_instantiation(self):
+        """Test that AI/ML API models can be instantiated correctly."""
+        model_names = [
+            "openai/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo",
+            "openai/anthropic/claude-3-5-sonnet-20241022",
+            "openai/mistralai/Mixtral-8x7B-Instruct-v0.1",
+            "openai/Qwen/Qwen2.5-72B-Instruct-Turbo",
+        ]
+        
+        for model_name in model_names:
+            llm = LLM(model=model_name)
+            assert llm.model == model_name
+            assert llm._get_custom_llm_provider() == "openai"
+            assert llm.get_context_window_size() > 0
+
+    @patch('crewai.llm.litellm.utils.supports_function_calling')
+    def test_aiml_api_function_calling_support(self, mock_supports_function_calling):
+        """Test function calling support detection for AI/ML API models."""
+        mock_supports_function_calling.return_value = True
+        
+        llm = LLM(model="openai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo")
+        supports_fc = llm.supports_function_calling()
+        
+        assert supports_fc is True
+        mock_supports_function_calling.assert_called_once_with(
+            "openai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
+            custom_llm_provider="openai"
+        )
+
+    def test_aiml_api_with_create_llm(self):
+        """Test that AI/ML API models work with create_llm utility."""
+        model_name = "openai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo"
+        llm = create_llm(model_name)
+        
+        assert isinstance(llm, LLM)
+        assert llm.model == model_name
+        assert llm._get_custom_llm_provider() == "openai"
+
+    def test_aiml_api_model_validation(self):
+        """Test that AI/ML API models pass validation checks."""
+        llm = LLM(model="openai/anthropic/claude-3-5-sonnet-20241022")
+        
+        llm._validate_call_params()
+        
+        llm_with_format = LLM(
+            model="openai/anthropic/claude-3-5-sonnet-20241022",
+            response_format={"type": "json_object"}
+        )
+        try:
+            llm_with_format._validate_call_params()
+        except ValueError as e:
+            assert "does not support response_format" in str(e)
+
+    def test_aiml_api_context_window_bounds(self):
+        """Test that AI/ML API model context windows are within valid bounds."""
+        from crewai.llm import LLM_CONTEXT_WINDOW_SIZES
+        
+        aiml_models = {k: v for k, v in LLM_CONTEXT_WINDOW_SIZES.items() 
+                      if k.startswith("openai/")}
+        
+        MIN_CONTEXT = 1024
+        MAX_CONTEXT = 2097152
+        
+        for model_name, context_size in aiml_models.items():
+            assert MIN_CONTEXT <= context_size <= MAX_CONTEXT, (
+                f"Model {model_name} context window {context_size} is outside "
+                f"valid bounds [{MIN_CONTEXT}, {MAX_CONTEXT}]"
+            )
+
+    def test_aiml_api_model_prefixes(self):
+        """Test that all AI/ML API models use the correct openai/ prefix."""
+        from crewai.llm import LLM_CONTEXT_WINDOW_SIZES
+        
+        aiml_models = [k for k in LLM_CONTEXT_WINDOW_SIZES.keys() 
+                      if k.startswith("openai/")]
+        
+        assert len(aiml_models) > 0, "No AI/ML API models found in context window sizes"
+        
+        for model_name in aiml_models:
+            assert model_name.startswith("openai/"), (
+                f"AI/ML API model {model_name} should start with 'openai/' prefix"
+            )
+            parts = model_name.split("/")
+            assert len(parts) >= 3, (
+                f"AI/ML API model {model_name} should have format 'openai/provider/model'"
+            )
+
+
+class TestAIMLAPIExamples:
+    """Test examples of using AI/ML API with CrewAI components."""
+
+    def test_aiml_api_with_agent_example(self):
+        """Test example usage of AI/ML API with CrewAI Agent."""
+        from crewai import Agent
+        
+        llm = LLM(model="openai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo")
+        
+        agent = Agent(
+            role="AI Assistant",
+            goal="Help users with their questions",
+            backstory="You are a helpful AI assistant powered by Llama 3.1",
+            llm=llm,
+        )
+        
+        assert agent.llm.model == "openai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo"
+        assert agent.llm._get_custom_llm_provider() == "openai"
+
+    def test_aiml_api_different_model_types(self):
+        """Test different types of models available through AI/ML API."""
+        model_types = {
+            "llama": "openai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
+            "claude": "openai/anthropic/claude-3-5-sonnet-20241022",
+            "mistral": "openai/mistralai/Mixtral-8x7B-Instruct-v0.1",
+            "qwen": "openai/Qwen/Qwen2.5-72B-Instruct-Turbo",
+            "deepseek": "openai/deepseek-ai/DeepSeek-V2.5",
+        }
+        
+        for model_type, model_name in model_types.items():
+            llm = LLM(model=model_name)
+            assert llm.model == model_name
+            assert llm._get_custom_llm_provider() == "openai"
+            assert llm.get_context_window_size() > 0, (
+                f"{model_type} model should have positive context window"
+            )