Paper Search MCP

Instructions

Implementation Reference

• paper_search_mcp/server.py:846-859 (handler)

  The MCP tool handler in server.py which delegates the reading request to the crossref_searcher instance.

  async def read_crossref_paper(paper_id: str, save_path: str = "./downloads") -> str:
      """Attempt to read and extract text content from a CrossRef paper.
  
      Args:
          paper_id: CrossRef DOI (e.g., '10.1038/nature12373').
          save_path: Directory where the PDF is/will be saved (default: './downloads').
      Returns:
          str: Message indicating that direct paper reading is not supported.
          
      Note:
          CrossRef is a citation database and doesn't provide direct paper content.
          Use the DOI to access the paper through the publisher's website.
      """
      return crossref_searcher.read_paper(paper_id, save_path)

• paper_search_mcp/academic_platforms/crossref.py:249-264 (handler)

  The implementation of read_paper in the CrossRefSearcher class, which explicitly returns an informative message that reading is not supported.

  def read_paper(self, paper_id: str, save_path: str = "./downloads") -> str:
      """
      CrossRef doesn't provide direct paper content access.
      
      Args:
          paper_id: DOI of the paper
          save_path: Directory for potential PDF storage (unused)
          
      Returns:
          str: Error message indicating PDF reading is not supported
      """
      message = ("CrossRef papers cannot be read directly through this tool. "
                "CrossRef is a citation database that provides metadata about academic papers. "
                "Only metadata and abstracts are available through CrossRef's API. "
                "To access the full text, please use the paper's DOI or URL to visit the publisher's website.")
      return message