get_docs
Search documentation for AI development libraries including LangChain, LlamaIndex, and OpenAI Agents SDK to find code examples and API references.
Instructions
搜索给定查询和库的最新文档。
支持 langchain、llama-index、autogen、agno、openai-agents-sdk、mcp-doc、camel-ai 和 crew-ai。
参数:
query: 要搜索的查询 (例如 "React Agent")
library: 要搜索的库 (例如 "agno")
返回:
文档中的文本Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| library | Yes |
Implementation Reference
- main.py:64-89 (handler)The main asynchronous handler function for the 'get_docs' tool. It validates the library, constructs a site-specific search query, fetches search results using Serper API, retrieves content from top results using BeautifulSoup, and returns the concatenated text.
@mcp.tool() async def get_docs(query: str, library: str): """ 搜索给定查询和库的最新文档。 支持 langchain、llama-index、autogen、agno、openai-agents-sdk、mcp-doc、camel-ai 和 crew-ai。 参数: query: 要搜索的查询 (例如 "React Agent") library: 要搜索的库 (例如 "agno") 返回: 文档中的文本 """ if library not in docs_urls: raise ValueError(f"Library {library} not supported by this tool") query = f"site:{docs_urls[library]} {query}" results = await search_web(query) if len(results["organic"]) == 0: return "No results found" text = "" for result in results["organic"]: text += await fetch_url(result["link"]) return text - main.py:64-64 (registration)The @mcp.tool() decorator registers the get_docs function as an MCP tool.
@mcp.tool() - main.py:36-53 (helper)Helper function to perform web search using Serper API, used by get_docs.
async def search_web(query: str) -> dict | None: payload = json.dumps({"q": query, "num": 2}) headers = { "X-API-KEY": os.getenv("SERPER_API_KEY"), "Content-Type": "application/json", } async with httpx.AsyncClient() as client: try: response = await client.post( SERPER_URL, headers=headers, data=payload, timeout=30.0 ) response.raise_for_status() return response.json() except httpx.TimeoutException: return {"organic": []} - main.py:54-63 (helper)Helper function to fetch and parse HTML content from a URL, used by get_docs.
async def fetch_url(url: str): async with httpx.AsyncClient() as client: try: response = await client.get(url, timeout=30.0) soup = BeautifulSoup(response.text, "html.parser") text = soup.get_text() return text except httpx.TimeoutException: return "Timeout error"