Paper Search MCP

Instructions

Implementation Reference

• paper_search_mcp/academic_platforms/biorxiv.py:121-144 (handler)

  Implementation of read_paper which downloads and extracts text from a bioRxiv PDF.

  def read_paper(self, paper_id: str, save_path: str = "./downloads") -> str:
      """
      Read a paper and convert it to text format.
      
      Args:
          paper_id: bioRxiv DOI
          save_path: Directory where the PDF is/will be saved
          
      Returns:
          str: The extracted text content of the paper
      """
      pdf_path = f"{save_path}/{paper_id.replace('/', '_')}.pdf"
      if not os.path.exists(pdf_path):
          pdf_path = self.download_pdf(paper_id, save_path)
      
      try:
          reader = PdfReader(pdf_path)
          text = ""
          for page in reader.pages:
              text += page.extract_text() + "\n"
          return text.strip()
      except Exception as e:
          print(f"Error reading PDF for paper {paper_id}: {e}")
          return ""

• paper_search_mcp/server.py:551-564 (handler)

  The MCP server wrapper for the read_biorxiv_paper tool that calls the BioRxivSearcher implementation.

  async def read_biorxiv_paper(paper_id: str, save_path: str = "./downloads") -> str:
      """Read and extract text content from a bioRxiv paper PDF.
  
      Args:
          paper_id: bioRxiv DOI.
          save_path: Directory where the PDF is/will be saved (default: './downloads').
      Returns:
          str: The extracted text content of the paper.
      """
      try:
          return biorxiv_searcher.read_paper(paper_id, save_path)
      except Exception as e:
          print(f"Error reading paper {paper_id}: {e}")
          return ""