All-in-MCP

Instructions

Implementation Reference

• src/apaper/server.py:104-122 (registration)

  Registration and handler for the MCP tool 'apaper_download_iacr_paper'. This thin wrapper calls the IACRSearcher.download_pdf method.

  @mcp.tool()
  def download_iacr_paper(paper_id: str, save_path: str = "./downloads") -> str:
      """
      Download PDF of an IACR ePrint paper
      
      Args:
          paper_id: IACR paper ID (e.g., '2009/101')
          save_path: Directory to save the PDF (default: './downloads')
      """
      try:
          result = iacr_searcher.download_pdf(paper_id, save_path)
          
          if result.startswith(("Error", "Failed")):
              return f"Download failed: {result}"
          else:
              return f"PDF downloaded successfully to: {result}"
      except Exception as e:
          return f"Error downloading IACR paper: {str(e)}"

• src/apaper/platforms/iacr.py:207-235 (handler)

  Core handler logic for downloading IACR paper PDFs. Constructs PDF URL, downloads the file, saves it locally, and returns the path or error.

  def download_pdf(self, paper_id: str, save_path: str) -> str:
      """
      Download PDF from IACR ePrint Archive
  
      Args:
          paper_id: IACR paper ID (e.g., "2025/1014")
          save_path: Path to save the PDF
  
      Returns:
          str: Path to downloaded file or error message
      """
      try:
          os.makedirs(save_path, exist_ok=True)
          pdf_url = f"{self.IACR_BASE_URL}/{paper_id}.pdf"
  
          response = self.session.get(pdf_url)
  
          if response.status_code == 200:
              filename = f"{save_path}/iacr_{paper_id.replace('/', '_')}.pdf"
              with open(filename, "wb") as f:
                  f.write(response.content)
              return filename
          else:
              return f"Failed to download PDF: HTTP {response.status_code}"
  
      except Exception as e:
          logger.error(f"PDF download error: {e}")
          return f"Error downloading PDF: {e}"

• src/apaper/server.py:25-28 (helper)

  Instantiation of the IACRSearcher instance used by the tool handlers.

  iacr_searcher = IACRSearcher()
  cryptobib_searcher = CryptoBibSearcher(cache_dir="./downloads")
  crossref_searcher = CrossrefSearcher()
  google_scholar_searcher = GoogleScholarSearcher()

• src/apaper/server.py:13-19 (helper)

  Imports for the platform searchers including IACRSearcher.

  from apaper.platforms import (
      IACRSearcher,
      CryptoBibSearcher,
      CrossrefSearcher,
      GoogleScholarSearcher
  )
  from apaper.utils.pdf_reader import read_pdf