MCP Fetch

Instructions

Implementation Reference

• src/mcp_fetch/server.py:160-189 (handler)

  The MCP tool handler for the 'fetch' tool. Processes arguments using Fetch schema, fetches content via fetch_url, handles pagination with start_index and max_length, truncation messages, and returns TextContent.

  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"))
  
  
      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}")]

• src/mcp_fetch/server.py:89-117 (schema)

  Pydantic BaseModel defining the 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.",
          ),
      ]

• src/mcp_fetch/server.py:133-144 (registration)

  Registration of the 'fetch' tool via the MCP Server's list_tools decorator, specifying name, description, and input schema.

      @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(),
              )
          ]

• src/mcp_fetch/server.py:49-87 (helper)

  Core helper function that performs the asynchronous HTTP GET request using httpx, handles errors, detects HTML content, and either extracts markdown or returns raw with prefix.

  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",
      )

• src/mcp_fetch/server.py:26-44 (helper)

  Helper function to simplify HTML content using readabilipy and convert to markdown using markdownify.

  def extract_content_from_html(html: str) -> str:
      """Extract and convert HTML content to Markdown format.
  
      Args:
          html: Raw HTML content to process
  
      Returns:
          Simplified markdown version of the content
      """
      ret = readabilipy.simple_json.simple_json_from_html_string(
          html, use_readability=True
      )
      if not ret["content"]:
          return "<error>Page failed to be simplified from HTML</error>"
      content = markdownify.markdownify(
          ret["content"],
          heading_style=markdownify.ATX,
      )
      return content