Paper Search MCP Server

Instructions

INSTEAD (try in order):
1. Visit paper URL - many NBER/Fed papers are freely available
2. read_scihub_paper(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:838-854 (handler)

  Handler function for 'read_repec_paper' tool. Registered via @mcp.tool() decorator. Delegates to generic _read function using RePECSearcher.read_paper.

  @mcp.tool()
  async def read_repec_paper(paper_id: str, save_path: Optional[str] = None) -> str:
      """RePEc/IDEAS does NOT support direct paper reading.
      
      INSTEAD (try in order):
      1. Visit paper URL - many NBER/Fed papers are freely available
      2. read_scihub_paper(doi) - if published before 2023
      
      Args:
          paper_id: RePEc handle (unused).
          save_path: Unused.
      
      Returns:
          Error message with alternatives.
      """
      return await _read('repec', paper_id, save_path)

• paper_find_mcp/academic_platforms/repec.py:593-611 (helper)

  The core implementation logic for reading RePEc papers in RePECSearcher.read_paper method, which provides an error response since direct reading is not supported.

  def read_paper(self, paper_id: str, save_path: str) -> str:
      """RePEc/IDEAS 不支持直接论文阅读
      
      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 papers cannot be read directly. "
          "Only metadata and abstracts are available through IDEAS. "
          "ALTERNATIVES:\n"
          "1. Visit the paper URL to access full text at the source\n"
          "2. If DOI is available, use read_scihub_paper(doi)\n"
          "3. Many working papers from NBER/Fed are freely downloadable"
      )

• paper_find_mcp/server.py:137-157 (helper)

  Generic _read helper function used by read_repec_paper and other platform-specific read tools to invoke the platform searcher's read_paper method.

  async def _read(
      searcher_name: str, 
      paper_id: str, 
      save_path: Optional[str] = None
  ) -> str:
      """通用阅读函数"""
      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.read_paper(paper_id, save_path)
      except NotImplementedError as e:
          return str(e)
      except Exception as e:
          logger.error(f"Read failed for {searcher_name}: {e}")
          return f"Error reading paper: {str(e)}"

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

  Global SEARCHERS dictionary registration where 'repec': RePECSearcher() instance is created for use by the _read function.

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