Paper Search MCP

Instructions

Implementation Reference

• paper_search_mcp/academic_platforms/biorxiv.py:86-120 (handler)

  The implementation of the download_pdf method within the BioRxivSearcher class, which handles the actual downloading of the PDF file from bioRxiv.

  def download_pdf(self, paper_id: str, save_path: str) -> str:
      """
      Download a PDF for a given paper ID from bioRxiv.
  
      Args:
          paper_id: The DOI of the paper.
          save_path: Directory to save the PDF.
  
      Returns:
          Path to the downloaded PDF file.
      """
      if not paper_id:
          raise ValueError("Invalid paper_id: paper_id is empty")
  
      pdf_url = f"https://www.biorxiv.org/content/{paper_id}v1.full.pdf"
      tries = 0
      while tries < self.max_retries:
          try:
              # Add User-Agent to avoid potential 403 errors
              headers = {
                  'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'
              }
              response = self.session.get(pdf_url, timeout=self.timeout, headers=headers)
              response.raise_for_status()
              os.makedirs(save_path, exist_ok=True)
              output_file = f"{save_path}/{paper_id.replace('/', '_')}.pdf"
              with open(output_file, 'wb') as f:
                  f.write(response.content)
              return output_file
          except requests.exceptions.RequestException as e:
              tries += 1
              if tries == self.max_retries:
                  raise Exception(f"Failed to download PDF after {self.max_retries} attempts: {e}")
              print(f"Attempt {tries} failed, retrying...")

• paper_search_mcp/server.py:482-491 (handler)

  The MCP tool handler for 'download_biorxiv' in server.py, which calls the download_pdf method of the BioRxivSearcher class.

  async def download_biorxiv(paper_id: str, save_path: str = "./downloads") -> str:
      """Download PDF of a bioRxiv paper.
  
      Args:
          paper_id: bioRxiv DOI.
          save_path: Directory to save the PDF (default: './downloads').
      Returns:
          Path to the downloaded PDF file.
      """
      return biorxiv_searcher.download_pdf(paper_id, save_path)