MCP Server Template for Cursor IDE

Instructions

Implementation Reference

• mcp_hitchcode/server.py:66-106 (handler)

  The core handler function that asynchronously fetches Railway CLI documentation from the given URL (default: https://docs.railway.app/guides/cli), returns the raw HTML as TextContent, and handles various errors like timeouts and HTTP errors.

  async def fetch_railway_docs(
      url: str = "https://docs.railway.app/guides/cli",
  ) -> list[types.TextContent]:
      """
      Fetch the most recent Railway CLI documentation.
      """
      headers = {
          "User-Agent": "MCP Railway Docs Fetcher (github.com/modelcontextprotocol/python-sdk)"
      }
  
      try:
          timeout = httpx.Timeout(10.0, connect=5.0)
          async with httpx.AsyncClient(
              follow_redirects=True, headers=headers, timeout=timeout
          ) as client:
              response = await client.get(url)
              response.raise_for_status()
  
              # Optionally, parse specific sections of the docs here
              return [types.TextContent(type="text", text=response.text)]
      except httpx.TimeoutException:
          return [
              types.TextContent(
                  type="text",
                  text="Error: Request timed out while trying to fetch the Railway CLI docs.",
              )
          ]
      except httpx.HTTPStatusError as e:
          return [
              types.TextContent(
                  type="text",
                  text=f"Error: HTTP {e.response.status_code} error while fetching the Railway CLI docs.",
              )
          ]
      except Exception as e:
          return [
              types.TextContent(
                  type="text", text=f"Error: Failed to fetch Railway CLI docs: {str(e)}"
              )
          ]

• mcp_hitchcode/server.py:433-435 (registration)

  Dispatch logic within the main @app.call_tool() handler (fetch_tool) that checks for the tool name 'fetch_railway_docs' and invokes the handler with the provided or default URL.

  if name == "fetch_railway_docs":
      url = arguments.get("url", "https://docs.railway.app/guides/cli")
      return await fetch_railway_docs(url)

• mcp_hitchcode/server.py:589-601 (registration)

  Tool object registration returned by @app.list_tools(), specifying the name, description, and input schema (optional 'url' parameter). This defines the tool for MCP clients.

  types.Tool(
      name="fetch_railway_docs",
      description="Fetches the most recent Railway CLI documentation. Optionally, provide a custom URL.",
      inputSchema={
          "type": "object",
          "properties": {
              "url": {
                  "type": "string",
                  "description": "Optional custom URL for fetching Railway CLI docs.",
              },
          },
      },
  ),

• mcp_hitchcode/server.py:592-600 (schema)

  Input schema definition for the 'fetch_railway_docs' tool, specifying an optional 'url' string property.

  inputSchema={
      "type": "object",
      "properties": {
          "url": {
              "type": "string",
              "description": "Optional custom URL for fetching Railway CLI docs.",
          },
      },
  },