Skeleton MCP Server

Instructions

Implementation Reference

• src/skeleton_mcp/api/example.py:39-78 (handler)

  The handler function that implements the list_items tool logic, including pagination, filtering, and mock data handling.

  async def list_items(
      page: int = 1,
      page_size: int = 10,
      filter_name: str | None = None,
  ) -> dict[str, Any]:
      """
      List all items with optional filtering and pagination.
  
      Args:
          page: Page number (1-indexed)
          page_size: Number of items per page
          filter_name: Optional filter by name (case-insensitive contains)
  
      Returns:
          A dictionary containing:
          - items: List of item objects
          - total: Total number of items matching the filter
          - page: Current page number
          - page_size: Number of items per page
      """
      # In a real implementation:
      # client = get_client()
      # return client.get("items", params={"page": page, "page_size": page_size})
  
      items = list(MOCK_ITEMS.values())
  
      if filter_name:
          items = [i for i in items if filter_name.lower() in i["name"].lower()]
  
      total = len(items)
      start = (page - 1) * page_size
      end = start + page_size
      items = items[start:end]
  
      return {
          "items": items,
          "total": total,
          "page": page,
          "page_size": page_size,
      }

• src/skeleton_mcp/server.py:89-89 (registration)

  The registration of the list_items tool using FastMCP by applying mcp.tool() to the imported example.list_items function.

  mcp.tool()(example.list_items)