Library Docs MCP Server

Instructions

Search the docs for a given query and library.
Supports langchain, llama-index, mcp, and openai.

Args:
    query: The query to search for (e.g. "Chroma DB")
    library: The library to search in (e.g. "langchain")

Returns:
    Text from the docs

Implementation Reference

• server.py:56-82 (handler)

  The main handler function for the 'get_docs' MCP tool. Decorated with @mcp.tool() for registration. Takes a query and library, constructs a site-specific search query, uses Serper API to find relevant docs pages, fetches their content using BeautifulSoup, and returns the concatenated text.

  @mcp.tool()
  async def get_docs(query: str, library: str):
      """
      Search the docs for a given query and library.
      Supports langchain, llama-index, mcp, and openai.
  
      Args:
          query: The query to search for (e.g. "Chroma DB")
          library: The library to search in (e.g. "langchain")
      
      Returns:
          Text from the docs
      """
      if library not in docs_urls:
          raise ValueError(f"Library {library} not supported by this tool")
  
      query = f"site:{docs_urls[library]} {query}" # Serper search format for searching in specified site
      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

• server.py:25-42 (helper)

  Helper function to perform web search using Serper API for the given query, returning search results or empty on timeout.

  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": []}

• server.py:45-54 (helper)

  Helper function to fetch content from a URL, parse with BeautifulSoup to extract text, handling timeouts.

  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"

• server.py:17-22 (helper)

  Dictionary mapping supported libraries to their documentation base URLs, used to construct site-specific search queries.

  docs_urls = {
      "langchain": "python.langchain.com/docs",
      "llama-index": "docs.llamaindex.ai/en/stable",
      "mcp": "modelcontextprotocol.io",
      "openai": "platform.openai.com/docs"
  }

• server.py:58-68 (schema)

  Tool schema and description provided in the docstring, defining input parameters (query: str, library: str) and output (text from docs).

  """
  Search the docs for a given query and library.
  Supports langchain, llama-index, mcp, and openai.
  
  Args:
      query: The query to search for (e.g. "Chroma DB")
      library: The library to search in (e.g. "langchain")
  
  Returns:
      Text from the docs
  """