Paper Search MCP

Instructions

Implementation Reference

• paper_search_mcp/server.py:1159-1170 (handler)

  MCP tool handler for 'read_base_paper'. It calls the 'read_paper' method of the 'base_searcher' instance.

  @mcp.tool()
  async def read_base_paper(paper_id: str, save_path: str = "./downloads") -> str:
      """Read and extract text content from a BASE paper.
  
      Args:
          paper_id: BASE paper identifier.
          save_path: Directory where the PDF is/will be saved (default: './downloads').
      Returns:
          str: Extracted text content.
      """
      return base_searcher.read_paper(paper_id, save_path)

• paper_search_mcp/academic_platforms/base_search.py:204-223 (handler)

  Implementation of 'read_paper' in BASESearcher, which wraps the base class 'read_paper' method to provide platform-specific error handling.

  def read_paper(self, paper_id: str, save_path: str = "./downloads") -> str:
      """Read paper text from PDF.
  
      Args:
          paper_id: Paper identifier
          save_path: Directory where PDF is/will be saved
  
      Returns:
          Extracted text content
  
      Raises:
          NotImplementedError: If PDF cannot be read
      """
      try:
          return super().read_paper(paper_id, save_path)
      except Exception as e:
          logger.error(f"Error reading BASE paper {paper_id}: {e}")
          raise NotImplementedError(
              f"Cannot read paper from BASE: {e}"
          )