PDF Tools MCP Server

Instructions

Supports both local file paths and URLs. For URLs, the PDF will be downloaded
to a temporary directory and cached for future use.

Args:
    pdf_file_path: Path to the PDF file or URL to PDF
    
Returns:
    Basic information about the PDF file

Implementation Reference

• pdf_tools_mcp/server.py:432-480 (handler)

  The `get_pdf_info` tool handler, which retrieves basic metadata and page count from a PDF file.

  @mcp.tool()
  async def get_pdf_info(pdf_file_path: str) -> str:
      """Get basic information about a PDF file including page count.
      
      Supports both local file paths and URLs. For URLs, the PDF will be downloaded
      to a temporary directory and cached for future use.
  
      Args:
          pdf_file_path: Path to the PDF file or URL to PDF
          
      Returns:
          Basic information about the PDF file
      """
      try:
          # Resolve path (download if URL, validate if local path)
          actual_path = resolve_path(pdf_file_path)
          
          # Validate local path if not URL
          if not is_url(pdf_file_path):
              is_valid, error_msg = validate_path(pdf_file_path)
              if not is_valid:
                  return error_msg
      
      except Exception as e:
          return f"Error resolving path: {str(e)}"
      
      try:
          with open(actual_path, 'rb') as file:
              pdf_reader = PyPDF2.PdfReader(file)
              
              # Get all needed information within the with block
              total_pages = len(pdf_reader.pages)
              info = pdf_reader.metadata
              
              result = "PDF file information:\n"
              result += f"Total pages: {total_pages}\n"
              
              if info:
                  result += f"Title: {info.get('/Title', 'Unknown')}\n"
                  result += f"Author: {info.get('/Author', 'Unknown')}\n"
                  result += f"Creator: {info.get('/Creator', 'Unknown')}\n"
                  result += f"Creation date: {info.get('/CreationDate', 'Unknown')}\n"
              
              return result
          
      except FileNotFoundError:
          return f"Error: File not found '{actual_path}'"
      except Exception as e:
          return f"Error getting PDF information: {str(e)}"