MCP Server Example

Instructions

Implementation Reference

• main.py:48-72 (handler)

  The core handler function for the 'get_docs' MCP tool. Registered via @mcp.tool() decorator. Performs site-specific Google search using Serper API and aggregates text content from top results.

  @mcp.tool()  
  async def get_docs(query: str, library: str):
    """
    Search the latest docs for a given query and library.
    Supports langchain, openai, and llama-index.
  
    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}"
    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:20-37 (helper)

  Helper function to perform web search using the Serper API, returning search results.

  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:38-47 (helper)

  Helper function to fetch content from a URL and extract plain text using BeautifulSoup.

  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"

• main.py:14-18 (helper)

  Configuration dictionary mapping supported library names to their documentation site URLs, used for site-specific searches.

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

• main.py:49-60 (schema)

  Type hints and docstring defining the input schema (query: str, library: str ∈ ['langchain','llama-index','openai']) and output (str: text from docs).

  async def get_docs(query: str, library: str):
    """
    Search the latest docs for a given query and library.
    Supports langchain, openai, and llama-index.
  
    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
    """