mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-07-04 22:49:23 +00:00
* feat: adopt directory-based docs versioning with Edge channel Switch docs.crewai.com from navigation-only versioning (every version selector entry rendered the same docs/<lang>/* source files) to Mintlify's directory-based versioning so each version selector entry renders its own snapshot. Add an "Edge" channel under docs/edge/<lang>/* that always reflects main HEAD for unreleased work, eliminating pre-release leakage onto frozen release labels. External links to canonical /<lang>/* URLs are preserved via wildcard redirects that always land on the current default version. Layout: - docs/edge/<lang>/* rolling source (you edit here) - docs/edge/enterprise-api.*.yaml - docs/v<X.Y.Z>/<lang>/* frozen, immutable snapshots - docs/v<X.Y.Z>/enterprise-api.*.yaml - docs/images/ shared, append-only - docs/docs.json nav + redirects URLs follow the Mintlify-idiomatic shape: /edge/<lang>/<page> for Edge, /v<X.Y.Z>/<lang>/<page> for every frozen snapshot. The wildcard redirects /<lang>/:slug* -> /<default>/<lang>/:slug* keep stale links working, and every freeze rewrites them (plus all per-section/per-page redirects) so destinations always resolve to the current default without depending on a second redirect hop. Release flow integration (devtools release): - New module crewai_devtools.docs_versioning.freeze() materialises docs/v<X.Y.Z>/ from docs/edge/, rewrites openapi: refs inside the snapshot, inserts the version into every language block in docs.json, and refreshes all redirect destinations. - _update_docs_and_create_pr() in cli.py now calls that freeze during Phase 2 of devtools release. Edge changelogs are updated first (so the snapshot freeze picks them up), then the snapshot is staged alongside docs.json, branched as docs/freeze-v<X.Y.Z>, and the PR is titled [docs-freeze] docs: snapshot and changelog for v<X.Y.Z> — the title prefix the new CI guard reads. - The PR still gates tag, GitHub release, PyPI publish, and the enterprise release as before; no new PRs are added. - Pre-releases (1.X.YaN, 1.X.YbN, ...) skip the snapshot — they ride Edge — and the docs PR title omits the [docs-freeze] prefix. - docs_check (AI-generated docs scaffolding) writes to docs/edge/<lang>/* so newly-generated unreleased docs land in Edge and never accidentally touch a frozen snapshot. Migration scripts (one-shot): - scripts/docs/freeze_historical_versions.py reconstructs all 16 historical snapshots (v1.10.0 .. v1.14.7) from git tags via git archive | tar, rewriting openapi: MDX refs so each snapshot reads its own enterprise-api YAML rather than the live one. - scripts/docs/prefix_version_paths.py one-shot-migrates docs.json: rewrites every page path in 16 versioned blocks to point under docs/v<X.Y.Z>/, inserts a new Edge entry per language, tags v1.14.7 as Latest (default), prunes pages whose target file doesn't exist in the snapshot (e.g. docs/ar/ didn't exist before v1.12.0), and writes the wildcard + per-section redirects. - scripts/docs/freeze_current_edge.py is now a thin CLI wrapper around docs_versioning.freeze for manual one-off freezes (e.g. retroactively snapshotting a forgotten release). CI guards (.github/workflows/docs-snapshots.yml): - Frozen snapshots under docs/v[0-9]*/ are immutable; only PRs whose title contains [docs-freeze] (i.e. release-cut PRs generated by devtools release or the manual wrapper) may modify them. - Images under docs/images/ are append-only since snapshots share a single image directory. Deleting or renaming an image breaks every historical snapshot that still references it. Restored docs/images/crewai-otel-export.png from PR #3673; it was deleted in PR #4908 but v1.10.0 / v1.10.1 snapshots still reference it. Restoring instead of editing the snapshots preserves historical rendering fidelity and validates the new append-only rule retroactively. Tests: - lib/devtools/tests/test_docs_versioning.py covers the freeze: file copy, openapi rewrite, version insertion, default demotion, redirect upserts, per-section redirect rewriting, idempotency, and invalid inputs. Verified locally with mintlify broken-links: 0 broken links across the full site (Edge + 16 frozen versions, 4 locales). AGENTS.md (repo root) is the contributor guide for the new model; RELEASING.md is the release-cut runbook; README's Contribution section links to both. Co-authored-by: Cursor <cursoragent@cursor.com> * style: resolve linter issues --------- Co-authored-by: Cursor <cursoragent@cursor.com>
151 lines
6.2 KiB
Plaintext
151 lines
6.2 KiB
Plaintext
---
|
|
title: Transporte SSE
|
|
description: Saiba como conectar o CrewAI a servidores MCP remotos usando Server-Sent Events (SSE) para comunicação em tempo real.
|
|
icon: wifi
|
|
mode: "wide"
|
|
---
|
|
|
|
## Visão Geral
|
|
|
|
Server-Sent Events (SSE) fornecem uma forma padrão para um servidor web enviar atualizações a um cliente através de uma única conexão HTTP de longa duração. No contexto do MCP, SSE é utilizado para que servidores remotos transmitam dados (como respostas de ferramentas) para sua aplicação CrewAI em tempo real.
|
|
|
|
## Conceitos-Chave
|
|
|
|
- **Servidores Remotos**: SSE é adequado para servidores MCP hospedados remotamente.
|
|
- **Fluxo Unidirecional**: Normalmente, SSE é um canal de comunicação de mão única, do servidor para o cliente.
|
|
- **Configuração do `MCPServerAdapter`**: Para SSE, você fornecerá a URL do servidor e especificará o tipo de transporte.
|
|
|
|
## Conectando via SSE
|
|
|
|
Você pode se conectar a um servidor MCP baseado em SSE usando duas abordagens principais para gerenciar o ciclo de vida da conexão:
|
|
|
|
### 1. Conexão Totalmente Gerenciada (Recomendado)
|
|
|
|
Utilizar um gerenciador de contexto Python (`with` statement) é a abordagem recomendada. Ele lida automaticamente com o estabelecimento e o encerramento da conexão com o servidor MCP SSE.
|
|
|
|
```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
|
|
agente_sse = Agent(
|
|
role="Usuário de Serviço Remoto",
|
|
goal="Utilizar uma ferramenta fornecida por um servidor MCP remoto via SSE.",
|
|
backstory="Um agente de IA que conecta a serviços externos via SSE.",
|
|
tools=tools,
|
|
reasoning=True,
|
|
verbose=True,
|
|
)
|
|
|
|
sse_task = Task(
|
|
description="Buscar atualizações em tempo real das ações 'AAPL' usando uma ferramenta SSE.",
|
|
expected_output="O preço mais recente da ação AAPL.",
|
|
agent=agente_sse,
|
|
markdown=True
|
|
)
|
|
|
|
sse_crew = Crew(
|
|
agents=[agente_sse],
|
|
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>
|
|
Substitua `"http://localhost:8000/sse"` pela URL real do seu servidor MCP SSE.
|
|
</Note>
|
|
|
|
### 2. Ciclo de Vida Manual da Conexão
|
|
|
|
Caso precise de um controle mais detalhado, você pode gerenciar manualmente o ciclo de vida da conexão do `MCPServerAdapter`.
|
|
|
|
<Info>
|
|
Você **DEVE** chamar `mcp_server_adapter.stop()` para garantir que a conexão seja encerrada e os recursos liberados. O uso de um bloco `try...finally` é altamente recomendado.
|
|
</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="Analista Remoto de Dados",
|
|
goal="Analisar dados obtidos de um servidor MCP remoto SSE usando gerenciamento manual de conexão.",
|
|
backstory="Um agente de IA especializado em gerenciar conexões SSE explicitamente.",
|
|
tools=tools,
|
|
verbose=True
|
|
)
|
|
|
|
analysis_task = Task(
|
|
description="Buscar e analisar as tendências mais recentes de atividade de usuários do servidor SSE.",
|
|
expected_output="Um relatório resumido das tendências de atividade dos usuários.",
|
|
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.")
|
|
|
|
```
|
|
|
|
## Considerações de Segurança para SSE
|
|
|
|
<Warning>
|
|
**Ataques de DNS Rebinding**: Transportes SSE podem ser vulneráveis a ataques de DNS rebinding se o servidor MCP não estiver devidamente protegido. Isso pode permitir que sites maliciosos interajam com servidores MCP locais ou da intranet.
|
|
</Warning>
|
|
|
|
Para mitigar esse risco:
|
|
- As implementações do servidor MCP devem **validar os cabeçalhos `Origin`** em conexões SSE recebidas.
|
|
- Ao rodar servidores MCP SSE locais para desenvolvimento, **faça o bind apenas em `localhost` (`127.0.0.1`)** ao invés de todas as interfaces de rede (`0.0.0.0`).
|
|
- Implemente **autenticação adequada** para todas as conexões SSE caso exponham ferramentas ou dados sensíveis.
|
|
|
|
Para uma visão abrangente das melhores práticas de segurança, consulte nossa página de [Considerações de Segurança](./security.mdx) e a documentação oficial [MCP Transport Security](https://modelcontextprotocol.io/docs/concepts/transports#security-considerations). |