Paper Search MCP

Instructions

Implementation Reference

• paper_search_mcp/server.py:1082-1091 (handler)

  This is the MCP tool handler for 'read_openaire_paper'. It delegates the call to the OpenAiresearcher instance.

  async def read_openaire_paper(paper_id: str, save_path: str = "./downloads") -> str:
      """Attempt to read and extract text content from an OpenAIRE paper.
  
      Args:
          paper_id: OpenAIRE paper identifier.
          save_path: Directory where the PDF is/will be saved (default: './downloads').
      Returns:
          str: Extracted text or error message.
      """
      return openaire_searcher.read_paper(paper_id, save_path)

• paper_search_mcp/academic_platforms/openaire.py:677-693 (handler)

  This is the implementation of 'read_paper' within the OpenAiresearcher class, which currently raises a NotImplementedError, indicating it is not yet supported for OpenAIRE.

  def read_paper(self, paper_id: str, save_path: str = "./downloads") -> str:
      """
      Download and extract text from an OpenAIRE paper.
  
      Args:
          paper_id: OpenAIRE paper identifier
          save_path: Directory where PDF is/will be saved
  
      Returns:
          Extracted text content of the paper
  
      Raises:
          NotImplementedError: If paper reading is not supported
      """
      raise NotImplementedError(
          f"{self.__class__.__name__} does not support direct paper reading."
      )