Paper Search MCP

Instructions

Implementation Reference

• paper_search_mcp/server.py:1133-1143 (handler)

  The tool registration and handler function 'read_doaj_paper' in the MCP server. It delegates to 'doaj_searcher.read_paper'.

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

• paper_search_mcp/academic_platforms/doaj.py:416-444 (handler)

  The actual implementation of 'read_paper' within the 'DOAJSearcher' class, which handles the PDF download and text extraction.

  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:
          # Try to download PDF first
          pdf_path = self.download_pdf(paper_id, save_path)
  
          # Extract text from PDF
          from PyPDF2 import PdfReader
          reader = PdfReader(pdf_path)
          text = ""
          for page in reader.pages:
              page_text = page.extract_text()
              if page_text:
                  text += page_text + "\n"
          return text.strip()
      except Exception as e:
          logger.error(f"Error reading DOAJ paper {paper_id}: {e}")
          raise NotImplementedError(