Paper Search MCP Server

Instructions

CrossRef is a metadata/citation database only - it does not host PDFs.

INSTEAD (try in order):
1. download_arxiv(id) - if arXiv preprint (always works)
2. download_scihub(doi) - if published before 2023
3. download_semantic(id) - last resort (may not have PDF)

Args:
    paper_id: DOI (e.g., '10.1038/nature12373').
    save_path: Unused.

Returns:
    Error message explaining alternatives.

Implementation Reference

• paper_find_mcp/server.py:686-704 (handler)

  Primary handler and registration for the 'download_crossref' MCP tool. Delegates to the generic _download function using the 'crossref' searcher.

  @mcp.tool()
  async def download_crossref(paper_id: str, save_path: Optional[str] = None) -> str:
      """CrossRef does NOT support direct PDF downloads.
      
      CrossRef is a metadata/citation database only - it does not host PDFs.
      
      INSTEAD (try in order):
      1. download_arxiv(id) - if arXiv preprint (always works)
      2. download_scihub(doi) - if published before 2023
      3. download_semantic(id) - last resort (may not have PDF)
      
      Args:
          paper_id: DOI (e.g., '10.1038/nature12373').
          save_path: Unused.
      
      Returns:
          Error message explaining alternatives.
      """
      return await _download('crossref', paper_id, save_path)

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

  Generic _download helper function used by all platform-specific download tools, including download_crossref. Calls searcher.download_pdf() and handles NotImplementedError.

  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/crossref.py:306-321 (helper)

  CrossRefSearcher.download_pdf method implementation. Raises NotImplementedError with detailed user guidance, as CrossRef is metadata-only.

  def download_pdf(self, paper_id: str, save_path: str) -> str:
      """
      CrossRef doesn't provide direct PDF downloads.
      
      Args:
          paper_id: DOI of the paper
          save_path: Directory to save the PDF
          
      Raises:
          NotImplementedError: Always raises this error as CrossRef doesn't provide direct PDF access
      """
      message = ("CrossRef does not provide direct PDF downloads. "
                "CrossRef is a citation database that provides metadata about academic papers. "
                "To access the full text, please use the paper's DOI or URL to visit the publisher's website.")
      raise NotImplementedError(message)

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

  Global SEARCHERS dictionary instantiating CrossRefSearcher() for use by download_crossref and other tools.

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