Paper Search MCP

Instructions

Implementation Reference

• paper_search_mcp/server.py:1049-1062 (handler)

  The tool `read_dblp_paper` is registered in `server.py`. It delegates the call to the `read_paper` method of the `dblp_searcher` instance.

  @mcp.tool()
  async def read_dblp_paper(paper_id: str, save_path: str = "./downloads") -> str:
      """Attempt to read and extract text content from a dblp paper.
  
      Note: dblp doesn't provide direct paper content access.
      This function returns an informative message.
  
      Args:
          paper_id: dblp paper identifier.
          save_path: Directory where the PDF would be saved (unused).
      Returns:
          str: Message indicating that direct paper reading is not supported.
      """
      return dblp_searcher.read_paper(paper_id, save_path)

• paper_search_mcp/academic_platforms/dblp.py:346-363 (handler)

  The `DBLPSearcher.read_paper` method, which is called by the `read_dblp_paper` tool, raises a `NotImplementedError` as dblp does not provide direct paper access.

  def read_paper(self, paper_id: str, save_path: str = "./downloads") -> str:
      """
      Download and extract text from a dblp paper.
  
      Args:
          paper_id: dblp paper identifier
          save_path: Directory where PDF is/will be saved
  
      Returns:
          Extracted text content of the paper
  
      Raises:
          NotImplementedError: dblp doesn't support direct paper reading
      """
      raise NotImplementedError(
          "dblp doesn't provide direct paper content access. "
          "Use DOI to access content from other sources."
      )