Paper Search MCP

Instructions

Implementation Reference

• paper_search_mcp/server.py:452-462 (handler)

  The 'download_arxiv' tool handler in the MCP server, which delegates the download task to the 'arxiv_searcher' instance.

  @mcp.tool()
  async def download_arxiv(paper_id: str, save_path: str = "./downloads") -> str:
      """Download PDF of an arXiv paper.
  
      Args:
          paper_id: arXiv paper ID (e.g., '2106.12345').
          save_path: Directory to save the PDF (default: './downloads').
      Returns:
          Path to the downloaded PDF file.
      """
      return await asyncio.to_thread(arxiv_searcher.download_pdf, paper_id, save_path)

• paper_search_mcp/academic_platforms/arxiv.py:81-88 (handler)

  The implementation of 'download_pdf' method in ArxivSearcher, which performs the actual HTTP request to download the PDF.

  def download_pdf(self, paper_id: str, save_path: str) -> str:
      pdf_url = f"https://arxiv.org/pdf/{paper_id}.pdf"
      response = requests.get(pdf_url)
      os.makedirs(save_path, exist_ok=True)
      output_file = f"{save_path}/{paper_id}.pdf"
      with open(output_file, 'wb') as f:
          f.write(response.content)
      return output_file