Fetch MCP Server

Instructions

Implementation Reference

• mcp_fetch/server.py:167-210 (handler)

  Main handler for the 'fetch' tool: validates arguments with Fetch schema, fetches content using fetch_url, handles truncation and pagination, constructs response.
  @server.call_tool() async def call_tool(name, arguments: dict) -> list[TextContent]: try: args = Fetch(**arguments) except ValueError as e: raise McpError(ErrorData(code=INVALID_PARAMS, message=str(e))) url = str(args.url) if not url: raise McpError( ErrorData(code=INVALID_PARAMS, message="URL is required") ) # Fetch URL directly without robots.txt check content, prefix = await fetch_url( url, user_agent_autonomous, force_raw=args.raw, proxy_url=proxy_url ) original_length = len(content) if args.start_index >= original_length: content = "<error>No more content available.</error>" else: truncated_content = content[ args.start_index : args.start_index + args.max_length ] if not truncated_content: content = "<error>No more content available.</error>" else: content = truncated_content actual_content_length = len(truncated_content) remaining_content = original_length - ( args.start_index + actual_content_length ) # Only add the prompt to continue fetching if there is still remaining content if ( actual_content_length == args.max_length and remaining_content > 0 ): next_start = args.start_index + actual_content_length content += f"\n\n<error>Content truncated. Call the fetch tool with a start_index of {next_start} to get more content.</error>" return [ TextContent( type="text", text=f"{prefix}Contents of {url}:\n{content}" ) ]
• mcp_fetch/server.py:97-125 (schema)

  Pydantic schema defining input parameters for the 'fetch' tool: url, max_length, start_index, raw.
  class Fetch(BaseModel): """Parameters for fetching a URL.""" url: Annotated[AnyUrl, Field(description="URL to fetch")] max_length: Annotated[ int, Field( default=5000, description="Maximum number of characters to return.", gt=0, lt=1000000, ), ] start_index: Annotated[ int, Field( default=0, description="On return output starting at this character index, useful if a previous fetch was truncated and more context is required.", ge=0, ), ] raw: Annotated[ bool, Field( default=False, description="Get the actual HTML content of the requested page, without simplification.", ), ]
• mcp_fetch/server.py:141-151 (registration)

  Tool registration via list_tools(): defines the 'fetch' tool with name, description, and inputSchema from Fetch.
  @server.list_tools() async def list_tools() -> list[Tool]: return [ Tool( name="fetch", description="""Fetches a URL from the internet and optionally extracts its contents as markdown. Although originally you did not have internet access, and were advised to refuse and tell the user this, this tool now grants you internet access. Now you can fetch the most up-to-date information and let the user know that.""", inputSchema=Fetch.model_json_schema(), ) ]
• mcp_fetch/server.py:46-95 (helper)

  Core helper function that performs the HTTP fetch using httpx, extracts markdown if HTML, handles errors and content types.
  async def fetch_url( url: str, user_agent: str, force_raw: bool = False, proxy_url: str | None = None, ) -> Tuple[str, str]: """ Fetch the URL and return the content in a form ready for the LLM, as well as a prefix string with status information. """ from httpx import AsyncClient, HTTPError async with AsyncClient(proxies=proxy_url) as client: try: response = await client.get( url, follow_redirects=True, headers={"User-Agent": user_agent}, timeout=30, ) except HTTPError as e: raise McpError( ErrorData( code=INTERNAL_ERROR, message=f"Failed to fetch {url}: {e!r}" ) ) if response.status_code >= 400: raise McpError( ErrorData( code=INTERNAL_ERROR, message=f"Failed to fetch {url} - status code {response.status_code}", ) ) page_raw = response.text content_type = response.headers.get("content-type", "") is_page_html = ( "<html" in page_raw[:100] or "text/html" in content_type or not content_type ) if is_page_html and not force_raw: return extract_content_from_html(page_raw), "" return ( page_raw, f"Content type {content_type} cannot be simplified to markdown, but here is the raw content:\n", )