Paper Search MCP Server

Instructions

Args:
    paper_id: medRxiv DOI (e.g., '10.1101/2024.01.01.12345678').
    save_path: Directory to save PDF.

Returns:
    Path to downloaded PDF.

Implementation Reference

• paper_find_mcp/server.py:401-412 (handler)

  The main handler function for the 'download_medrxiv' tool. It is registered via @mcp.tool() decorator and delegates the download to the generic _download helper using the 'medrxiv' searcher instance.

  @mcp.tool()
  async def download_medrxiv(paper_id: str, save_path: Optional[str] = None) -> str:
      """Download PDF from medRxiv (free and open access).
      
      Args:
          paper_id: medRxiv DOI (e.g., '10.1101/2024.01.01.12345678').
          save_path: Directory to save PDF.
      
      Returns:
          Path to downloaded PDF.
      """
      return await _download('medrxiv', paper_id, save_path)

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

  Generic download helper function that retrieves the appropriate searcher from SEARCHERS dict and calls its download_pdf method. This is called by all download_* tool handlers.

  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/academic_platforms/medrxiv.py:176-212 (helper)

  The core implementation of PDF download for medRxiv papers in the MedRxivSearcher class. Downloads the PDF from the constructed URL https://www.medrxiv.org/content/{paper_id}v1.full.pdf and saves it to the specified path.

  def download_pdf(self, paper_id: str, save_path: str) -> str:
      """下载 PDF
      
      Args:
          paper_id: medRxiv DOI
          save_path: 保存目录
          
      Returns:
          下载的文件路径或错误信息
      """
      if not paper_id:
          return "Error: paper_id is empty"
      
      pdf_url = f"https://www.medrxiv.org/content/{paper_id}v1.full.pdf"
      
      try:
          response = self.session.get(
              pdf_url, 
              timeout=self.timeout,
              headers={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'}
          )
          response.raise_for_status()
          
          os.makedirs(save_path, exist_ok=True)
          filename = f"{paper_id.replace('/', '_')}.pdf"
          pdf_path = os.path.join(save_path, filename)
          
          with open(pdf_path, 'wb') as f:
              f.write(response.content)
          
          logger.info(f"PDF downloaded: {pdf_path}")
          return pdf_path
          
      except Exception as e:
          logger.error(f"PDF download failed: {e}")
          return f"Error downloading PDF: {e}"

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

  Global SEARCHERS dictionary where the 'medrxiv' key is registered with a MedRxivSearcher instance, which provides the download_pdf method used by the tool.

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