Paper Search MCP

Instructions

Implementation Reference

• paper_search_mcp/server.py:466-478 (handler)

  The 'download_pubmed' tool handler in the MCP server, which wraps the platform-specific 'download_pdf' call.

  async def download_pubmed(paper_id: str, save_path: str = "./downloads") -> str:
      """Attempt to download PDF of a PubMed paper.
  
      Args:
          paper_id: PubMed ID (PMID).
          save_path: Directory to save the PDF (default: './downloads').
      Returns:
          str: Message indicating that direct PDF download is not supported.
      """
      try:
          return pubmed_searcher.download_pdf(paper_id, save_path)
      except NotImplementedError as e:
          return str(e)

• paper_search_mcp/academic_platforms/pubmed.py:94-109 (handler)

  The 'download_pdf' implementation in the PubMedSearcher class, which explicitly raises a NotImplementedError as PubMed does not support direct PDF downloads.

  def download_pdf(self, paper_id: str, save_path: str) -> str:
      """Attempt to download a paper's PDF from PubMed.
  
      Args:
          paper_id: PubMed ID (PMID)
          save_path: Directory to save the PDF
  
      Returns:
          str: Error message indicating PDF download is not supported
      
      Raises:
          NotImplementedError: Always raises this error as PubMed doesn't provide direct PDF access
      """
      message = ("PubMed does not provide direct PDF downloads. "
                "Please use the paper's DOI or URL to access the publisher's website.")
      raise NotImplementedError(message)