Paper Search MCP Server

Instructions

RePEc is a metadata index - PDFs are hosted at original institutions.

INSTEAD (try in order):
1. Visit paper URL - many NBER/Fed papers are freely available
2. download_scihub(doi) - if published before 2023

Args:
    paper_id: RePEc handle (unused).
    save_path: Unused.

Returns:
    Error message with alternatives.

Implementation Reference

• paper_find_mcp/server.py:818-836 (handler)

  MCP tool handler for 'download_repec'. Decorated with @mcp.tool() for registration. Delegates to generic _download using RePECSearcher.

  @mcp.tool()
  async def download_repec(paper_id: str, save_path: Optional[str] = None) -> str:
      """RePEc/IDEAS does NOT support direct PDF downloads.
      
      RePEc is a metadata index - PDFs are hosted at original institutions.
      
      INSTEAD (try in order):
      1. Visit paper URL - many NBER/Fed papers are freely available
      2. download_scihub(doi) - if published before 2023
      
      Args:
          paper_id: RePEc handle (unused).
          save_path: Unused.
      
      Returns:
          Error message with alternatives.
      """
      return await _download('repec', paper_id, save_path)

• paper_find_mcp/academic_platforms/repec.py:571-592 (helper)

  The platform-specific download_pdf method in RePECSearcher class, called by the generic _download. Returns an informative error message explaining limitations and alternatives.

  def download_pdf(self, paper_id: str, save_path: str) -> str:
      """RePEc/IDEAS 不支持直接 PDF 下载
      
      RePEc 是元数据索引，不托管 PDF 文件。
      PDF 通常在原机构网站（如 NBER、央行官网）。
      
      Args:
          paper_id: RePEc handle (未使用)
          save_path: 保存路径 (未使用)
          
      Returns:
          str: 错误信息和替代方案
      """
      return (
          "RePEc/IDEAS does not host PDF files directly. "
          "PDFs are available from the original institution's website. "
          "ALTERNATIVES:\n"
          "1. Use the paper URL to visit the source (NBER, Fed, etc.)\n"
          "2. If DOI is available, use download_scihub(doi)\n"
          "3. Many NBER/Fed working papers are freely available at source"
      )

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

  Generic _download helper function used by all platform-specific download tools, including download_repec. Dispatches to searcher.download_pdf.

  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:75-84 (registration)

  Global SEARCHERS dictionary instantiation, registering the RePECSearcher() instance for the 'repec' platform used by download_repec.

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