mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-01-07 15:18:29 +00:00
* feat: add `apps` & `actions` attributes to Agent (#3504)
* feat: add app attributes to Agent
* feat: add actions attribute to Agent
* chore: resolve linter issues
* refactor: merge the apps and actions parameters into a single one
* fix: remove unnecessary print
* feat: logging error when CrewaiPlatformTools fails
* chore: export CrewaiPlatformTools directly from crewai_tools
* style: resolver linter issues
* test: fix broken tests
* style: solve linter issues
* fix: fix broken test
* feat: monorepo restructure and test/ci updates
- Add crewai workspace member
- Fix vcr cassette paths and restore test dirs
- Resolve ci failures and update linter/pytest rules
* chore: update python version to 3.13 and package metadata
* feat: add crewai-tools workspace and fix tests/dependencies
* feat: add crewai-tools workspace structure
* Squashed 'temp-crewai-tools/' content from commit 9bae5633
git-subtree-dir: temp-crewai-tools
git-subtree-split: 9bae56339096cb70f03873e600192bd2cd207ac9
* feat: configure crewai-tools workspace package with dependencies
* fix: apply ruff auto-formatting to crewai-tools code
* chore: update lockfile
* fix: don't allow tool tests yet
* fix: comment out extra pytest flags for now
* fix: remove conflicting conftest.py from crewai-tools tests
* fix: resolve dependency conflicts and test issues
- Pin vcrpy to 7.0.0 to fix pytest-recording compatibility
- Comment out types-requests to resolve urllib3 conflict
- Update requests requirement in crewai-tools to >=2.32.0
* chore: update CI workflows and docs for monorepo structure
* chore: update CI workflows and docs for monorepo structure
* fix: actions syntax
* chore: ci publish and pin versions
* fix: add permission to action
* chore: bump version to 1.0.0a1 across all packages
- Updated version to 1.0.0a1 in pyproject.toml for crewai and crewai-tools
- Adjusted version in __init__.py files for consistency
* WIP: v1 docs (#3626)
(cherry picked from commit d46e20fa09bcd2f5916282f5553ddeb7183bd92c)
* docs: parity for all translations
* docs: full name of acronym AMP
* docs: fix lingering unused code
* docs: expand contextual options in docs.json
* docs: add contextual action to request feature on GitHub (#3635)
* chore: apply linting fixes to crewai-tools
* feat: add required env var validation for brightdata
Co-authored-by: Greyson Lalonde <greyson.r.lalonde@gmail.com>
* fix: handle properly anyOf oneOf allOf schema's props
Co-authored-by: Greyson Lalonde <greyson.r.lalonde@gmail.com>
* feat: bump version to 1.0.0a2
* Lorenze/native inference sdks (#3619)
* ruff linted
* using native sdks with litellm fallback
* drop exa
* drop print on completion
* Refactor LLM and utility functions for type consistency
- Updated `max_tokens` parameter in `LLM` class to accept `float` in addition to `int`.
- Modified `create_llm` function to ensure consistent type hints and return types, now returning `LLM | BaseLLM | None`.
- Adjusted type hints for various parameters in `create_llm` and `_llm_via_environment_or_fallback` functions for improved clarity and type safety.
- Enhanced test cases to reflect changes in type handling and ensure proper instantiation of LLM instances.
* fix agent_tests
* fix litellm tests and usagemetrics fix
* drop print
* Refactor LLM event handling and improve test coverage
- Removed commented-out event emission for LLM call failures in `llm.py`.
- Added `from_agent` parameter to `CrewAgentExecutor` for better context in LLM responses.
- Enhanced test for LLM call failure to simulate OpenAI API failure and updated assertions for clarity.
- Updated agent and task ID assertions in tests to ensure they are consistently treated as strings.
* fix test_converter
* fixed tests/agents/test_agent.py
* Refactor LLM context length exception handling and improve provider integration
- Renamed `LLMContextLengthExceededException` to `LLMContextLengthExceededExceptionError` for clarity and consistency.
- Updated LLM class to pass the provider parameter correctly during initialization.
- Enhanced error handling in various LLM provider implementations to raise the new exception type.
- Adjusted tests to reflect the updated exception name and ensure proper error handling in context length scenarios.
* Enhance LLM context window handling across providers
- Introduced CONTEXT_WINDOW_USAGE_RATIO to adjust context window sizes dynamically for Anthropic, Azure, Gemini, and OpenAI LLMs.
- Added validation for context window sizes in Azure and Gemini providers to ensure they fall within acceptable limits.
- Updated context window size calculations to use the new ratio, improving consistency and adaptability across different models.
- Removed hardcoded context window sizes in favor of ratio-based calculations for better flexibility.
* fix test agent again
* fix test agent
* feat: add native LLM providers for Anthropic, Azure, and Gemini
- Introduced new completion implementations for Anthropic, Azure, and Gemini, integrating their respective SDKs.
- Added utility functions for tool validation and extraction to support function calling across LLM providers.
- Enhanced context window management and token usage extraction for each provider.
- Created a common utility module for shared functionality among LLM providers.
* chore: update dependencies and improve context management
- Removed direct dependency on `litellm` from the main dependencies and added it under extras for better modularity.
- Updated the `litellm` dependency specification to allow for greater flexibility in versioning.
- Refactored context length exception handling across various LLM providers to use a consistent error class.
- Enhanced platform-specific dependency markers for NVIDIA packages to ensure compatibility across different systems.
* refactor(tests): update LLM instantiation to include is_litellm flag in test cases
- Modified multiple test cases in test_llm.py to set the is_litellm parameter to True when instantiating the LLM class.
- This change ensures that the tests are aligned with the latest LLM configuration requirements and improves consistency across test scenarios.
- Adjusted relevant assertions and comments to reflect the updated LLM behavior.
* linter
* linted
* revert constants
* fix(tests): correct type hint in expected model description
- Updated the expected description in the test_generate_model_description_dict_field function to use 'Dict' instead of 'dict' for consistency with type hinting conventions.
- This change ensures that the test accurately reflects the expected output format for model descriptions.
* refactor(llm): enhance LLM instantiation and error handling
- Updated the LLM class to include validation for the model parameter, ensuring it is a non-empty string.
- Improved error handling by logging warnings when the native SDK fails, allowing for a fallback to LiteLLM.
- Adjusted the instantiation of LLM in test cases to consistently include the is_litellm flag, aligning with recent changes in LLM configuration.
- Modified relevant tests to reflect these updates, ensuring better coverage and accuracy in testing scenarios.
* fixed test
* refactor(llm): enhance token usage tracking and add copy methods
- Updated the LLM class to track token usage and log callbacks in streaming mode, improving monitoring capabilities.
- Introduced shallow and deep copy methods for the LLM instance, allowing for better management of LLM configurations and parameters.
- Adjusted test cases to instantiate LLM with the is_litellm flag, ensuring alignment with recent changes in LLM configuration.
* refactor(tests): reorganize imports and enhance error messages in test cases
- Cleaned up import statements in test_crew.py for better organization and readability.
- Enhanced error messages in test cases to use `re.escape` for improved regex matching, ensuring more robust error handling.
- Adjusted comments for clarity and consistency across test scenarios.
- Ensured that all necessary modules are imported correctly to avoid potential runtime issues.
* feat: add base devtooling
* fix: ensure dep refs are updated for devtools
* fix: allow pre-release
* feat: allow release after tag
* feat: bump versions to 1.0.0a3
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
* fix: match tag and release title, ignore devtools build for pypi
* fix: allow failed pypi publish
* feat: introduce trigger listing and execution commands for local development (#3643)
* chore: exclude tests from ruff linting
* chore: exclude tests from GitHub Actions linter
* fix: replace print statements with logger in agent and memory handling
* chore: add noqa for intentional print in printer utility
* fix: resolve linting errors across codebase
* feat: update docs with new approach to consume Platform Actions (#3675)
* fix: remove duplicate line and add explicit env var
* feat: bump versions to 1.0.0a4 (#3686)
* Update triggers docs (#3678)
* docs: introduce triggers list & triggers run command
* docs: add KO triggers docs
* docs: ensure CREWAI_PLATFORM_INTEGRATION_TOKEN is mentioned on docs (#3687)
* Lorenze/bedrock llm (#3693)
* feat: add AWS Bedrock support and update dependencies
- Introduced BedrockCompletion class for AWS Bedrock integration in LLM.
- Added boto3 as a new dependency in both pyproject.toml and uv.lock.
- Updated LLM class to support Bedrock provider.
- Created new files for Bedrock provider implementation.
* using converse api
* converse
* linted
* refactor: update BedrockCompletion class to improve parameter handling
- Changed max_tokens from a fixed integer to an optional integer.
- Simplified model ID assignment by removing the inference profile mapping method.
- Cleaned up comments and unnecessary code related to tool specifications and model-specific parameters.
* feat: improve event bus thread safety and async support
Add thread-safe, async-compatible event bus with read–write locking and
handler dependency ordering. Remove blinker dependency and implement
direct dispatch. Improve type safety, error handling, and deterministic
event synchronization.
Refactor tests to auto-wait for async handlers, ensure clean teardown,
and add comprehensive concurrency coverage. Replace thread-local state
in AgentEvaluator with instance-based locking for correct cross-thread
access. Enhance tracing reliability and event finalization.
* feat: enhance OpenAICompletion class with additional client parameters (#3701)
* feat: enhance OpenAICompletion class with additional client parameters
- Added support for default_headers, default_query, and client_params in the OpenAICompletion class.
- Refactored client initialization to use a dedicated method for client parameter retrieval.
- Introduced new test cases to validate the correct usage of OpenAICompletion with various parameters.
* fix: correct test case for unsupported OpenAI model
- Updated the test_openai.py to ensure that the LLM instance is created before calling the method, maintaining proper error handling for unsupported models.
- This change ensures that the test accurately checks for the NotFoundError when an invalid model is specified.
* fix: enhance error handling in OpenAICompletion class
- Added specific exception handling for NotFoundError and APIConnectionError in the OpenAICompletion class to provide clearer error messages and improve logging.
- Updated the test case for unsupported models to ensure it raises a ValueError with the appropriate message when a non-existent model is specified.
- This change improves the robustness of the OpenAI API integration and enhances the clarity of error reporting.
* fix: improve test for unsupported OpenAI model handling
- Refactored the test case in test_openai.py to create the LLM instance after mocking the OpenAI client, ensuring proper error handling for unsupported models.
- This change enhances the clarity of the test by accurately checking for ValueError when a non-existent model is specified, aligning with recent improvements in error handling for the OpenAICompletion class.
* feat: bump versions to 1.0.0b1 (#3706)
* Lorenze/tools drop litellm (#3710)
* completely drop litellm and correctly pass config for qdrant
* feat: add support for additional embedding models in EmbeddingService
- Expanded the list of supported embedding models to include Google Vertex, Hugging Face, Jina, Ollama, OpenAI, Roboflow, Watson X, custom embeddings, Sentence Transformers, Text2Vec, OpenClip, and Instructor.
- This enhancement improves the versatility of the EmbeddingService by allowing integration with a wider range of embedding providers.
* fix: update collection parameter handling in CrewAIRagAdapter
- Changed the condition for setting vectors_config in the CrewAIRagAdapter to check for QdrantConfig instance instead of using hasattr. This improves type safety and ensures proper configuration handling for Qdrant integration.
* moved stagehand as optional dep (#3712)
* feat: bump versions to 1.0.0b2 (#3713)
* feat: enhance AnthropicCompletion class with additional client parame… (#3707)
* feat: enhance AnthropicCompletion class with additional client parameters and tool handling
- Added support for client_params in the AnthropicCompletion class to allow for additional client configuration.
- Refactored client initialization to use a dedicated method for retrieving client parameters.
- Implemented a new method to handle tool use conversation flow, ensuring proper execution and response handling.
- Introduced comprehensive test cases to validate the functionality of the AnthropicCompletion class, including tool use scenarios and parameter handling.
* drop print statements
* test: add fixture to mock ANTHROPIC_API_KEY for tests
- Introduced a pytest fixture to automatically mock the ANTHROPIC_API_KEY environment variable for all tests in the test_anthropic.py module.
- This change ensures that tests can run without requiring a real API key, improving test isolation and reliability.
* refactor: streamline streaming message handling in AnthropicCompletion class
- Removed the 'stream' parameter from the API call as it is set internally by the SDK.
- Simplified the handling of tool use events and response construction by extracting token usage from the final message.
- Enhanced the flow for managing tool use conversation, ensuring proper integration with the streaming API response.
* fix streaming here too
* fix: improve error handling in tool conversion for AnthropicCompletion class
- Enhanced exception handling during tool conversion by catching KeyError and ValueError.
- Added logging for conversion errors to aid in debugging and maintain robustness in tool integration.
* feat: enhance GeminiCompletion class with client parameter support (#3717)
* feat: enhance GeminiCompletion class with client parameter support
- Added support for client_params in the GeminiCompletion class to allow for additional client configuration.
- Refactored client initialization into a dedicated method for improved parameter handling.
- Introduced a new method to retrieve client parameters, ensuring compatibility with the base class.
- Enhanced error handling during client initialization to provide clearer messages for missing configuration.
- Updated documentation to reflect the changes in client parameter usage.
* add optional dependancies
* refactor: update test fixture to mock GOOGLE_API_KEY
- Renamed the fixture from `mock_anthropic_api_key` to `mock_google_api_key` to reflect the change in the environment variable being mocked.
- This update ensures that all tests in the module can run with a mocked GOOGLE_API_KEY, improving test isolation and reliability.
* fix tests
* feat: enhance BedrockCompletion class with advanced features
* feat: enhance BedrockCompletion class with advanced features and error handling
- Added support for guardrail configuration, additional model request fields, and custom response field paths in the BedrockCompletion class.
- Improved error handling for AWS exceptions and added token usage tracking with stop reason logging.
- Enhanced streaming response handling with comprehensive event management, including tool use and content block processing.
- Updated documentation to reflect new features and initialization parameters.
- Introduced a new test suite for BedrockCompletion to validate functionality and ensure robust integration with AWS Bedrock APIs.
* chore: add boto typing
* fix: use typing_extensions.Required for Python 3.10 compatibility
---------
Co-authored-by: Greyson Lalonde <greyson.r.lalonde@gmail.com>
* feat: azure native tests
* feat: add Azure AI Inference support and related tests
- Introduced the `azure-ai-inference` package with version `1.0.0b9` and its dependencies in `uv.lock` and `pyproject.toml`.
- Added new test files for Azure LLM functionality, including tests for Azure completion and tool handling.
- Implemented comprehensive test cases to validate Azure-specific behavior and integration with the CrewAI framework.
- Enhanced the testing framework to mock Azure credentials and ensure proper isolation during tests.
* feat: enhance AzureCompletion class with Azure OpenAI support
- Added support for the Azure OpenAI endpoint in the AzureCompletion class, allowing for flexible endpoint configurations.
- Implemented endpoint validation and correction to ensure proper URL formats for Azure OpenAI deployments.
- Enhanced error handling to provide clearer messages for common HTTP errors, including authentication and rate limit issues.
- Updated tests to validate the new endpoint handling and error messaging, ensuring robust integration with Azure AI Inference.
- Refactored parameter preparation to conditionally include the model parameter based on the endpoint type.
* refactor: convert project module to metaclass with full typing
* Lorenze/OpenAI base url backwards support (#3723)
* fix: enhance OpenAICompletion class base URL handling
- Updated the base URL assignment in the OpenAICompletion class to prioritize the new `api_base` attribute and fallback to the environment variable `OPENAI_BASE_URL` if both are not set.
- Added `api_base` to the list of parameters in the OpenAICompletion class to ensure proper configuration and flexibility in API endpoint management.
* feat: enhance OpenAICompletion class with api_base support
- Added the `api_base` parameter to the OpenAICompletion class to allow for flexible API endpoint configuration.
- Updated the `_get_client_params` method to prioritize `base_url` over `api_base`, ensuring correct URL handling.
- Introduced comprehensive tests to validate the behavior of `api_base` and `base_url` in various scenarios, including environment variable fallback.
- Enhanced test coverage for client parameter retrieval, ensuring robust integration with the OpenAI API.
* fix: improve OpenAICompletion class configuration handling
- Added a debug print statement to log the client configuration parameters during initialization for better traceability.
- Updated the base URL assignment logic to ensure it defaults to None if no valid base URL is provided, enhancing robustness in API endpoint configuration.
- Refined the retrieval of the `api_base` environment variable to streamline the configuration process.
* drop print
* feat: improvements on import native sdk support (#3725)
* feat: add support for Anthropic provider and enhance logging
- Introduced the `anthropic` package with version `0.69.0` in `pyproject.toml` and `uv.lock`, allowing for integration with the Anthropic API.
- Updated logging in the LLM class to provide clearer error messages when importing native providers, enhancing debugging capabilities.
- Improved error handling in the AnthropicCompletion class to guide users on installation via the updated error message format.
- Refactored import error handling in other provider classes to maintain consistency in error messaging and installation instructions.
* feat: enhance LLM support with Bedrock provider and update dependencies
- Added support for the `bedrock` provider in the LLM class, allowing integration with AWS Bedrock APIs.
- Updated `uv.lock` to replace `boto3` with `bedrock` in the dependencies, reflecting the new provider structure.
- Introduced `SUPPORTED_NATIVE_PROVIDERS` to include `bedrock` and ensure proper error handling when instantiating native providers.
- Enhanced error handling in the LLM class to raise informative errors when native provider instantiation fails.
- Added tests to validate the behavior of the new Bedrock provider and ensure fallback mechanisms work correctly for unsupported providers.
* test: update native provider fallback tests to expect ImportError
* adjust the test with the expected bevaior - raising ImportError
* this is exoecting the litellm format, all gemini native tests are in test_google.py
---------
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
* fix: remove stdout prints, improve test determinism, and update trace handling
Removed `print` statements from the `LLMStreamChunkEvent` handler to prevent
LLM response chunks from being written directly to stdout. The listener now
only tracks chunks internally.
Fixes #3715
Added explicit return statements for trace-related tests.
Updated cassette for `test_failed_evaluation` to reflect new behavior where
an empty trace dict is used instead of returning early.
Ensured deterministic cleanup order in test fixtures by making
`clear_event_bus_handlers` depend on `setup_test_environment`. This guarantees
event bus shutdown and file handle cleanup occur before temporary directory
deletion, resolving intermittent “Directory not empty” errors in CI.
* chore: remove lib/crewai exclusion from pre-commit hooks
* feat: enhance task guardrail functionality and validation
* feat: enhance task guardrail functionality and validation
- Introduced support for multiple guardrails in the Task class, allowing for sequential processing of guardrails.
- Added a new `guardrails` field to the Task model to accept a list of callable guardrails or string descriptions.
- Implemented validation to ensure guardrails are processed correctly, including handling of retries and error messages.
- Enhanced the `_invoke_guardrail_function` method to manage guardrail execution and integrate with existing task output processing.
- Updated tests to cover various scenarios involving multiple guardrails, including success, failure, and retry mechanisms.
This update improves the flexibility and robustness of task execution by allowing for more complex validation scenarios.
* refactor: enhance guardrail type handling in Task model
- Updated the Task class to improve guardrail type definitions, introducing GuardrailType and GuardrailsType for better clarity and type safety.
- Simplified the validation logic for guardrails, ensuring that both single and multiple guardrails are processed correctly.
- Enhanced error messages for guardrail validation to provide clearer feedback when incorrect types are provided.
- This refactor improves the maintainability and robustness of task execution by standardizing guardrail handling.
* feat: implement per-guardrail retry tracking in Task model
- Introduced a new private attribute `_guardrail_retry_counts` to the Task class for tracking retry attempts on a per-guardrail basis.
- Updated the guardrail processing logic to utilize the new retry tracking, allowing for independent retry counts for each guardrail.
- Enhanced error handling to provide clearer feedback when guardrails fail validation after exceeding retry limits.
- Modified existing tests to validate the new retry tracking behavior, ensuring accurate assertions on guardrail retries.
This update improves the robustness and flexibility of task execution by allowing for more granular control over guardrail validation and retry mechanisms.
* chore: 1.0.0b3 bump (#3734)
* chore: full ruff and mypy
improved linting, pre-commit setup, and internal architecture. Configured Ruff to respect .gitignore, added stricter rules, and introduced a lock pre-commit hook with virtualenv activation. Fixed type shadowing in EXASearchTool using a type_ alias to avoid PEP 563 conflicts and resolved circular imports in agent executor and guardrail modules. Removed agent-ops attributes, deprecated watson alias, and dropped crewai-enterprise tools with corresponding test updates. Refactored cache and memoization for thread safety and cleaned up structured output adapters and related logic.
* New MCL DSL (#3738)
* Adding MCP implementation
* New tests for MCP implementation
* fix tests
* update docs
* Revert "New tests for MCP implementation"
This reverts commit 0bbe6dee90.
* linter
* linter
* fix
* verify mcp pacakge exists
* adjust docs to be clear only remote servers are supported
* reverted
* ensure args schema generated properly
* properly close out
---------
Co-authored-by: lorenzejay <lorenzejaytech@gmail.com>
Co-authored-by: Greyson Lalonde <greyson.r.lalonde@gmail.com>
* feat: a2a experimental
experimental a2a support
---------
Co-authored-by: Lucas Gomide <lucaslg200@gmail.com>
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
Co-authored-by: Tony Kipkemboi <iamtonykipkemboi@gmail.com>
Co-authored-by: Mike Plachta <mplachta@users.noreply.github.com>
Co-authored-by: João Moura <joaomdmoura@gmail.com>
342 lines
13 KiB
Plaintext
342 lines
13 KiB
Plaintext
---
|
|
title: 'CrewAI에서 MCP 서버를 도구로 활용하기'
|
|
description: '`crewai-tools` 라이브러리를 사용하여 MCP 서버를 CrewAI agent에 도구로 통합하는 방법을 알아봅니다.'
|
|
icon: plug
|
|
mode: "wide"
|
|
---
|
|
|
|
## 개요
|
|
|
|
[Model Context Protocol](https://modelcontextprotocol.io/introduction) (MCP)는 AI 에이전트가 MCP 서버로 알려진 외부 서비스와 통신함으로써 LLM에 컨텍스트를 제공할 수 있도록 표준화된 방식을 제공합니다.
|
|
|
|
CrewAI는 MCP 통합을 위한 **두 가지 접근 방식**을 제공합니다:
|
|
|
|
### 🚀 **새로운 기능: 간단한 DSL 통합** (권장)
|
|
|
|
에이전트에 `mcps` 필드를 직접 사용하여 완벽한 MCP 도구 통합을 구현하세요:
|
|
|
|
```python
|
|
from crewai import Agent
|
|
|
|
agent = Agent(
|
|
role="연구 분석가",
|
|
goal="정보를 연구하고 분석",
|
|
backstory="외부 도구에 접근할 수 있는 전문가 연구원",
|
|
mcps=[
|
|
"https://mcp.exa.ai/mcp?api_key=your_key", # 외부 MCP 서버
|
|
"https://api.weather.com/mcp#get_forecast", # 서버의 특정 도구
|
|
"crewai-amp:financial-data", # CrewAI AMP 마켓플레이스
|
|
"crewai-amp:research-tools#pubmed_search" # 특정 AMP 도구
|
|
]
|
|
)
|
|
# MCP 도구들이 이제 자동으로 에이전트에서 사용 가능합니다!
|
|
```
|
|
|
|
### 🔧 **고급: MCPServerAdapter** (복잡한 시나리오용)
|
|
|
|
수동 연결 관리가 필요한 고급 사용 사례의 경우 `crewai-tools` 라이브러리는 `MCPServerAdapter` 클래스를 제공합니다.
|
|
|
|
현재 다음과 같은 전송 메커니즘을 지원합니다:
|
|
|
|
- **HTTPS**: 원격 서버용 (HTTPS를 통한 보안 통신)
|
|
- **Server-Sent Events (SSE)**: 원격 서버용 (서버에서 클라이언트로의 일방향, 실시간 데이터 스트리밍, HTTP 기반)
|
|
- **Streamable HTTP**: 원격 서버용 (유연하며 잠재적으로 양방향 통신이 가능, 주로 SSE를 활용한 서버-클라이언트 스트림 제공, HTTP 기반)
|
|
|
|
## 비디오 튜토리얼
|
|
CrewAI와 MCP 통합에 대한 종합적인 안내를 위해 이 비디오 튜토리얼을 시청하세요:
|
|
|
|
<iframe
|
|
className="w-full aspect-video rounded-xl"
|
|
src="https://www.youtube.com/embed/TpQ45lAZh48"
|
|
title="CrewAI MCP Integration Guide"
|
|
frameBorder="0"
|
|
allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture"
|
|
allowFullScreen
|
|
></iframe>
|
|
|
|
## 설치
|
|
|
|
`crewai-tools`와 함께 MCP를 사용하기 전에, 아래 명령어를 통해 `mcp` 추가 `crewai-tools` 종속성을 설치해야 합니다:
|
|
|
|
```shell
|
|
uv pip install 'crewai-tools[mcp]'
|
|
```
|
|
|
|
## 주요 개념 및 시작하기
|
|
|
|
`crewai-tools`의 `MCPServerAdapter` 클래스는 MCP 서버에 연결하고 해당 도구들을 CrewAI 에이전트에서 사용할 수 있도록 하는 기본 방법입니다. 다양한 전송 메커니즘을 지원하며 연결 관리를 간소화합니다.
|
|
|
|
파이썬 컨텍스트 매니저(`with` 문)를 사용하는 것이 `MCPServerAdapter`를 위한 **권장 방법**입니다. 이를 통해 MCP 서버와의 연결 시작 및 종료가 자동으로 처리됩니다.
|
|
|
|
## 연결 구성
|
|
|
|
`MCPServerAdapter`는 연결 동작을 맞춤화할 수 있는 여러 구성 옵션을 지원합니다:
|
|
|
|
- **`connect_timeout`** (선택 사항): MCP 서버에 연결을 설정하기 위해 대기할 최대 시간(초 단위)입니다. 명시하지 않으면 기본값은 30초입니다. 응답 시간이 가변적인 원격 서버에 특히 유용합니다.
|
|
|
|
```python
|
|
# 사용자 지정 연결 타임아웃 예시
|
|
with MCPServerAdapter(server_params, connect_timeout=60) as tools:
|
|
# 60초 이내에 연결이 설정되지 않으면 타임아웃 발생
|
|
pass
|
|
```
|
|
|
|
```python
|
|
from crewai import Agent
|
|
from crewai_tools import MCPServerAdapter
|
|
from mcp import StdioServerParameters # Stdio 서버용
|
|
|
|
# 예시 server_params (서버 유형에 따라 하나 선택):
|
|
# 1. Stdio 서버:
|
|
server_params=StdioServerParameters(
|
|
command="python3",
|
|
args=["servers/your_server.py"],
|
|
env={"UV_PYTHON": "3.12", **os.environ},
|
|
)
|
|
|
|
# 2. SSE 서버:
|
|
server_params = {
|
|
"url": "http://localhost:8000/sse",
|
|
"transport": "sse"
|
|
}
|
|
|
|
# 3. 스트림 가능 HTTP 서버:
|
|
server_params = {
|
|
"url": "http://localhost:8001/mcp",
|
|
"transport": "streamable-http"
|
|
}
|
|
|
|
# 예시 사용법 (server_params 설정 후 주석 해제 및 적용):
|
|
with MCPServerAdapter(server_params, connect_timeout=60) as mcp_tools:
|
|
print(f"Available tools: {[tool.name for tool in mcp_tools]}")
|
|
|
|
my_agent = Agent(
|
|
role="MCP Tool User",
|
|
goal="MCP 서버의 도구를 활용합니다.",
|
|
backstory="나는 MCP 서버에 연결하여 해당 도구를 사용할 수 있습니다.",
|
|
tools=mcp_tools, # 불러온 도구를 Agent에 전달
|
|
reasoning=True,
|
|
verbose=True
|
|
)
|
|
# ... 나머지 crew 설정 ...
|
|
```
|
|
이 일반적인 패턴은 도구를 통합하는 방법을 보여줍니다. 각 transport에 맞춘 구체적인 예시는 아래의 상세 가이드를 참고하세요.
|
|
|
|
## 필터링 도구
|
|
|
|
도구를 필터링하는 방법에는 두 가지가 있습니다:
|
|
|
|
1. 딕셔너리 스타일의 인덱싱을 사용하여 특정 도구에 접근하기.
|
|
2. 도구 이름 목록을 `MCPServerAdapter` 생성자에 전달하기.
|
|
|
|
### 딕셔너리 스타일 인덱싱을 사용하여 특정 도구에 접근하기
|
|
|
|
```python
|
|
with MCPServerAdapter(server_params, connect_timeout=60) 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["tool_name"]], # Pass the loaded tools to your agent
|
|
reasoning=True,
|
|
verbose=True
|
|
)
|
|
# ... rest of your crew setup ...
|
|
```
|
|
|
|
### `MCPServerAdapter` 생성자에 도구 이름의 리스트를 전달하세요.
|
|
|
|
```python
|
|
with MCPServerAdapter(server_params, "tool_name", connect_timeout=60) 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 ...
|
|
```
|
|
|
|
## CrewBase와 함께 사용하기
|
|
|
|
CrewBase 클래스 내에서 MCPServer 도구를 사용하려면 `get_mcp_tools` 메서드를 사용하세요. 서버 구성은 `mcp_server_params` 속성을 통해 제공되어야 합니다. 단일 구성 또는 여러 서버 구성을 리스트 형태로 전달할 수 있습니다.
|
|
|
|
```python
|
|
@CrewBase
|
|
class CrewWithMCP:
|
|
# ... 에이전트 및 작업 구성 파일 정의 ...
|
|
|
|
mcp_server_params = [
|
|
# 스트리머블 HTTP 서버
|
|
{
|
|
"url": "http://localhost:8001/mcp",
|
|
"transport": "streamable-http"
|
|
},
|
|
# SSE 서버
|
|
{
|
|
"url": "http://localhost:8000/sse",
|
|
"transport": "sse"
|
|
},
|
|
# StdIO 서버
|
|
StdioServerParameters(
|
|
command="python3",
|
|
args=["servers/your_stdio_server.py"],
|
|
env={"UV_PYTHON": "3.12", **os.environ},
|
|
)
|
|
]
|
|
|
|
@agent
|
|
def your_agent(self):
|
|
return Agent(config=self.agents_config["your_agent"], tools=self.get_mcp_tools()) # 모든 사용 가능한 도구 가져오기
|
|
|
|
# ... 나머지 crew 설정 ...
|
|
```
|
|
|
|
<Tip>
|
|
`@CrewBase`로 데코레이션된 클래스에서는 어댑터 수명 주기가 자동으로 관리됩니다.
|
|
|
|
- `get_mcp_tools()`가 처음 호출될 때 공유 `MCPServerAdapter`가 지연 생성되며 crew 내 모든 에이전트가 이를 재사용합니다.
|
|
- `.kickoff()`가 끝나면 `@CrewBase`가 주입한 after-kickoff 훅이 어댑터를 종료하므로 별도의 정리 코드가 필요 없습니다.
|
|
- `mcp_server_params`를 지정하지 않으면 `get_mcp_tools()`는 빈 리스트를 반환하여 MCP 설정 여부와 상관없이 동일한 코드 경로를 사용할 수 있습니다.
|
|
|
|
따라서 여러 에이전트에서 `get_mcp_tools()`를 호출하거나 환경에 따라 MCP 사용을 토글하더라도 안전하게 동작합니다.
|
|
</Tip>
|
|
|
|
### 연결 타임아웃 구성
|
|
|
|
`mcp_connect_timeout` 클래스 속성을 설정하여 MCP 서버의 연결 타임아웃을 구성할 수 있습니다. 타임아웃을 지정하지 않으면 기본값으로 30초가 사용됩니다.
|
|
|
|
```python
|
|
@CrewBase
|
|
class CrewWithMCP:
|
|
mcp_server_params = [...]
|
|
mcp_connect_timeout = 60 # 모든 MCP 연결에 60초 타임아웃
|
|
|
|
@agent
|
|
def your_agent(self):
|
|
return Agent(config=self.agents_config["your_agent"], tools=self.get_mcp_tools())
|
|
```
|
|
|
|
```python
|
|
@CrewBase
|
|
class CrewWithDefaultTimeout:
|
|
mcp_server_params = [...]
|
|
# mcp_connect_timeout 지정하지 않음 - 기본 30초 사용
|
|
|
|
@agent
|
|
def your_agent(self):
|
|
return Agent(config=self.agents_config["your_agent"], tools=self.get_mcp_tools())
|
|
```
|
|
|
|
### 도구 필터링
|
|
|
|
`get_mcp_tools` 메서드에 도구 이름의 리스트를 전달하여, 에이전트에 제공되는 도구를 필터링할 수 있습니다.
|
|
|
|
```python
|
|
@agent
|
|
def another_agent(self):
|
|
return Agent(
|
|
config=self.agents_config["your_agent"],
|
|
tools=self.get_mcp_tools("tool_1", "tool_2") # 특정 도구만 가져오기
|
|
)
|
|
```
|
|
|
|
타임아웃 구성은 crew 내의 모든 MCP 도구 호출에 적용됩니다:
|
|
|
|
```python
|
|
@CrewBase
|
|
class CrewWithCustomTimeout:
|
|
mcp_server_params = [...]
|
|
mcp_connect_timeout = 90 # 모든 MCP 연결에 90초 타임아웃
|
|
|
|
@agent
|
|
def filtered_agent(self):
|
|
return Agent(
|
|
config=self.agents_config["your_agent"],
|
|
tools=self.get_mcp_tools("tool_1", "tool_2") # 사용자 지정 타임아웃으로 특정 도구
|
|
)
|
|
```
|
|
|
|
## MCP 통합 탐색
|
|
|
|
<CardGroup cols={2}>
|
|
<Card
|
|
title="Stdio 전송"
|
|
icon="server"
|
|
href="/ko/mcp/stdio"
|
|
color="#3B82F6"
|
|
>
|
|
표준 입력/출력을 통해 로컬 MCP 서버에 연결합니다. 스크립트와 로컬 실행 파일에 이상적입니다.
|
|
</Card>
|
|
<Card
|
|
title="SSE 전송"
|
|
icon="wifi"
|
|
href="/ko/mcp/sse"
|
|
color="#10B981"
|
|
>
|
|
실시간 데이터 스트리밍을 위해 Server-Sent Events를 사용하여 원격 MCP 서버와 통합합니다.
|
|
</Card>
|
|
<Card
|
|
title="스트림 가능한 HTTP 전송"
|
|
icon="globe"
|
|
href="/ko/mcp/streamable-http"
|
|
color="#F59E0B"
|
|
>
|
|
유연한 스트림 가능한 HTTP를 활용하여 원격 MCP 서버와 안정적으로 통신할 수 있습니다.
|
|
</Card>
|
|
<Card
|
|
title="다중 서버 연결"
|
|
icon="layer-group"
|
|
href="/ko/mcp/multiple-servers"
|
|
color="#8B5CF6"
|
|
>
|
|
하나의 어댑터를 사용하여 여러 MCP 서버의 도구를 동시에 통합할 수 있습니다.
|
|
</Card>
|
|
<Card
|
|
title="보안 고려사항"
|
|
icon="lock"
|
|
href="/ko/mcp/security"
|
|
color="#EF4444"
|
|
>
|
|
에이전트를 안전하게 보호하기 위한 MCP 통합의 중요한 보안 모범 사례를 검토하세요.
|
|
</Card>
|
|
</CardGroup>
|
|
|
|
CrewAI와의 MCP 통합에 대한 전체 데모와 예제를 보려면 이 저장소를 확인하세요! 👇
|
|
|
|
<Card
|
|
title="GitHub 저장소"
|
|
icon="github"
|
|
href="https://github.com/tonykipkemboi/crewai-mcp-demo"
|
|
target="_blank"
|
|
>
|
|
CrewAI MCP 데모
|
|
</Card>
|
|
|
|
## MCP와 함께 안전하게 사용하기
|
|
<Warning>
|
|
항상 MCP 서버를 사용하기 전에 해당 서버를 신뢰할 수 있는지 확인하세요.
|
|
</Warning>
|
|
|
|
#### 보안 경고: DNS 리바인딩 공격
|
|
SSE 전송은 적절하게 보안되지 않은 경우 DNS 리바인딩 공격에 취약할 수 있습니다.
|
|
이를 방지하려면 다음을 수행하세요:
|
|
|
|
1. **항상 Origin 헤더를 검증**하여 들어오는 SSE 연결이 예상한 소스에서 오는지 확인합니다.
|
|
2. **서버를 모든 네트워크 인터페이스**(0.0.0.0)에 바인딩하는 것을 피하고, 로컬에서 실행할 때는 localhost(127.0.0.1)에만 바인딩합니다.
|
|
3. **모든 SSE 연결에 대해 적절한 인증을 구현**합니다.
|
|
|
|
이러한 보호 조치가 없으면 공격자가 원격 웹사이트에서 로컬 MCP 서버와 상호작용하기 위해 DNS 리바인딩을 사용할 수 있습니다.
|
|
|
|
자세한 내용은 [Anthropic의 MCP 전송 보안 문서](https://modelcontextprotocol.io/docs/concepts/transports#security-considerations)를 참고하세요.
|
|
|
|
### 제한 사항
|
|
* **지원되는 프리미티브**: 현재 `MCPServerAdapter`는 주로 MCP `tools`를 어댑팅하는 기능을 지원합니다. 다른 MCP 프리미티브(예: `prompts` 또는 `resources`)는 현재 이 어댑터를 통해 CrewAI 컴포넌트로 직접 통합되어 있지 않습니다.
|
|
* **출력 처리**: 어댑터는 일반적으로 MCP tool의 주요 텍스트 출력(예: `.content[0].text`)을 처리합니다. 복잡하거나 멀티모달 출력의 경우 이 패턴에 맞지 않으면 별도의 커스텀 처리가 필요할 수 있습니다.
|