Paper Search MCP Server

Instructions

PubMed is a metadata database - it does not host PDFs.

INSTEAD (try in order):
1. download_scihub(doi) - if published before 2023
2. download_semantic(id) - last resort

Args:
    paper_id: PMID (unused).
    save_path: Unused.

Returns:
    Error message with alternatives.

Implementation Reference

• paper_find_mcp/server.py:263-280 (handler)

  Handler function for download_pubmed tool. Registered via @mcp.tool(). Delegates to _download helper with 'pubmed' platform. Includes input schema via type hints and comprehensive docstring explaining limitations.

  @mcp.tool()
  async def download_pubmed(paper_id: str, save_path: Optional[str] = None) -> str:
      """PubMed does NOT support direct PDF downloads.
      
      PubMed is a metadata database - it does not host PDFs.
      
      INSTEAD (try in order):
      1. download_scihub(doi) - if published before 2023
      2. download_semantic(id) - last resort
      
      Args:
          paper_id: PMID (unused).
          save_path: Unused.
      
      Returns:
          Error message with alternatives.
      """
      return await _download('pubmed', paper_id, save_path)

• paper_find_mcp/server.py:115-134 (helper)

  Generic _download helper function called by download_pubmed. Retrieves the platform searcher (PubMedSearcher for 'pubmed') from SEARCHERS dict and invokes its download_pdf method, handling errors including 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/pubmed.py:323-336 (helper)

  PubMedSearcher.download_pdf method, the core platform-specific implementation called by the generic _download. Raises NotImplementedError with helpful message since PubMed is metadata-only.

  def download_pdf(self, paper_id: str, save_path: str) -> str:
      """尝试下载 PubMed 论文 PDF（不支持）
  
      PubMed 是索引数据库，不提供直接 PDF 下载。
      请使用 DOI 或 PubMed Central 获取全文。
      
      Raises:
          NotImplementedError: 始终抛出
      """
      raise NotImplementedError(
          "PubMed does not provide direct PDF downloads. "
          "Please use the paper's DOI to access the publisher's website, "
          "or check if the paper is available on PubMed Central (PMC)."
      )

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

  SEARCHERS dictionary that instantiates all platform searchers, including PubMedSearcher for the 'pubmed' key used by download_pubmed.

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