ScrapeGraph MCP Server

Instructions

Implementation Reference

• src/scrapegraph_mcp/server.py:1355-1396 (handler)

  MCP tool handler function for the 'markdownify' tool. It retrieves the API key, creates a ScapeGraphClient instance, and calls its markdownify method to convert the given website URL to markdown.
  @mcp.tool(annotations={"readOnlyHint": True, "destructiveHint": False, "idempotentHint": True}) def markdownify(website_url: str, ctx: Context) -> Dict[str, Any]: """ Convert a webpage into clean, formatted markdown. This tool fetches any webpage and converts its content into clean, readable markdown format. Useful for extracting content from documentation, articles, and web pages for further processing. Costs 2 credits per page. Read-only operation with no side effects. Args: website_url (str): The complete URL of the webpage to convert to markdown format. - Must include protocol (http:// or https://) - Supports most web content types (HTML, articles, documentation) - Works with both static and dynamic content - Examples: * https://example.com/page * https://docs.python.org/3/tutorial/ * https://github.com/user/repo/README.md - Invalid examples: * example.com (missing protocol) * ftp://example.com (unsupported protocol) * localhost:3000 (missing protocol) Returns: Dictionary containing: - markdown: The converted markdown content as a string - metadata: Additional information about the conversion (title, description, etc.) - status: Success/error status of the operation - credits_used: Number of credits consumed (always 2 for this operation) Raises: ValueError: If website_url is malformed or missing protocol HTTPError: If the webpage cannot be accessed or returns an error TimeoutError: If the webpage takes too long to load (>120 seconds) """ try: api_key = get_api_key(ctx) client = ScapeGraphClient(api_key) return client.markdownify(website_url) except Exception as e: return {"error": str(e)}
• src/scrapegraph_mcp/server.py:93-115 (helper)

  Core helper method in ScapeGraphClient class that performs the HTTP POST request to the ScrapeGraph API's /markdownify endpoint with the website_url, returning the JSON response containing the markdown.
  def markdownify(self, website_url: str) -> Dict[str, Any]: """ Convert a webpage into clean, formatted markdown. Args: website_url: URL of the webpage to convert Returns: Dictionary containing the markdown result """ url = f"{self.BASE_URL}/markdownify" data = { "website_url": website_url } response = self.client.post(url, headers=self.headers, json=data) if response.status_code != 200: error_msg = f"Error {response.status_code}: {response.text}" raise Exception(error_msg) return response.json()
• src/scrapegraph_mcp/server.py:1355-1355 (registration)

  Registration of the 'markdownify' tool using the @mcp.tool decorator on the FastMCP instance.
  @mcp.tool(annotations={"readOnlyHint": True, "destructiveHint": False, "idempotentHint": True})