Paper Search MCP Server

Instructions

Args:
    paper_id: IACR ID (e.g., '2024/123', '2009/101').
    save_path: Directory to save PDF.

Returns:
    Path to downloaded PDF.

Example:
    download_iacr("2024/123")

Implementation Reference

• paper_find_mcp/server.py:510-524 (handler)

  MCP tool handler and registration for download_iacr. Defines input schema via type hints and docstring, delegates to generic _download using 'iacr' searcher.

  @mcp.tool()
  async def download_iacr(paper_id: str, save_path: Optional[str] = None) -> str:
      """Download PDF from IACR ePrint (always free).
      
      Args:
          paper_id: IACR ID (e.g., '2024/123', '2009/101').
          save_path: Directory to save PDF.
      
      Returns:
          Path to downloaded PDF.
      
      Example:
          download_iacr("2024/123")
      """
      return await _download('iacr', paper_id, save_path)

• paper_find_mcp/academic_platforms/iacr.py:206-233 (handler)

  Exact implementation of the PDF download logic in IACRSearcher class, constructing the PDF URL and performing the HTTP download.

  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:
          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}"

• paper_find_mcp/server.py:115-135 (helper)

  Generic download helper function that dispatches to the specific platform's searcher.download_pdf method.

  async def _download(
      searcher_name: str, 
      paper_id: str, 
      save_path: Optional[str] = None
  ) -> str:
      """通用下载函数"""
      if save_path is None:
          save_path = get_download_path()
      
      searcher = SEARCHERS.get(searcher_name)
      if not searcher:
          return f"Error: Unknown searcher {searcher_name}"
      
      try:
          return searcher.download_pdf(paper_id, save_path)
      except NotImplementedError as e:
          return str(e)
      except Exception as e:
          logger.error(f"Download failed for {searcher_name}: {e}")
          return f"Error downloading: {str(e)}"

• paper_find_mcp/server.py:75-85 (helper)

  Global SEARCHERS dictionary that instantiates and provides the IACRSearcher instance under the 'iacr' key for use by download handlers.

  SEARCHERS = {
      'arxiv': ArxivSearcher(),
      'pubmed': PubMedSearcher(),
      'biorxiv': BioRxivSearcher(),
      'medrxiv': MedRxivSearcher(),
      'google_scholar': GoogleScholarSearcher(),
      'iacr': IACRSearcher(),
      'semantic': SemanticSearcher(),
      'crossref': CrossRefSearcher(),
      'repec': RePECSearcher(),
  }