ArXiv MCP Server

Instructions

Implementation Reference

• src/arxiv_mcp_server/tools/read_paper.py:32-81 (handler)

  The main handler function that executes the read_paper tool: validates paper existence, reads markdown content from storage, and returns JSON-wrapped result.

  async def handle_read_paper(arguments: Dict[str, Any]) -> List[types.TextContent]:
      """Handle requests to read a paper's content."""
      try:
          paper_ids = list_papers()
          paper_id = arguments["paper_id"]
          # Check if paper exists
          if paper_id not in paper_ids:
              return [
                  types.TextContent(
                      type="text",
                      text=json.dumps(
                          {
                              "status": "error",
                              "message": f"Paper {paper_id} not found in storage. You may need to download it first using download_paper.",
                          }
                      ),
                  )
              ]
  
          # Get paper content
          content = Path(settings.STORAGE_PATH, f"{paper_id}.md").read_text(
              encoding="utf-8"
          )
  
          return [
              types.TextContent(
                  type="text",
                  text=json.dumps(
                      {
                          "status": "success",
                          "paper_id": paper_id,
                          "content": content,
                      }
                  ),
              )
          ]
  
      except Exception as e:
          return [
              types.TextContent(
                  type="text",
                  text=json.dumps(
                      {
                          "status": "error",
                          "message": f"Error reading paper: {str(e)}",
                      }
                  ),
              )
          ]

• src/arxiv_mcp_server/tools/read_paper.py:11-24 (schema)

  Defines the input schema for the read_paper tool, specifying the required 'paper_id' parameter.

  read_tool = types.Tool(
      name="read_paper",
      description="Read the full content of a stored paper in markdown format",
      inputSchema={
          "type": "object",
          "properties": {
              "paper_id": {
                  "type": "string",
                  "description": "The arXiv ID of the paper to read",
              }
          },
          "required": ["paper_id"],
      },
  )

• src/arxiv_mcp_server/server.py:41-44 (registration)

  Registers the read_paper tool (as read_tool) in the MCP server's list_tools() method.

  @server.list_tools()
  async def list_tools() -> List[types.Tool]:
      """List available arXiv research tools."""
      return [search_tool, download_tool, list_tool, read_tool]

• src/arxiv_mcp_server/server.py:58-59 (registration)

  Dispatches calls to the 'read_paper' tool to the handle_read_paper handler in the MCP server's call_tool() method.

  elif name == "read_paper":
      return await handle_read_paper(arguments)

• src/arxiv_mcp_server/tools/read_paper.py:27-29 (helper)

  Helper function to list all stored paper IDs, used by the handler to check existence.

  def list_papers() -> list[str]:
      """List all stored paper IDs."""
      return [p.stem for p in Path(settings.STORAGE_PATH).glob("*.md")]