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.

Note: Avoid reading too many pages at once (recommended: <50 pages) to prevent errors.

Args:
    pdf_file_path: Path to the PDF file or URL to PDF
    start_page: Starting page number (default: 1)
    end_page: Ending page number (default: 1)
    
Returns:
    Extracted text content from the specified pages

Implementation Reference

• pdf_tools_mcp/server.py:380-430 (handler)

  The `read_pdf_pages` tool implementation in `pdf_tools_mcp/server.py`. It handles input validation, path resolution (supporting local files and URLs), and delegates text extraction to the `extract_text_from_pdf` helper function.

  @mcp.tool()
  async def read_pdf_pages(pdf_file_path: str, start_page: int = 1, end_page: int = 1) -> str:
      """Read content from PDF file for specified page range.
      
      Supports both local file paths and URLs. For URLs, the PDF will be downloaded
      to a temporary directory and cached for future use.
      
      Note: Avoid reading too many pages at once (recommended: <50 pages) to prevent errors.
  
      Args:
          pdf_file_path: Path to the PDF file or URL to PDF
          start_page: Starting page number (default: 1)
          end_page: Ending page number (default: 1)
          
      Returns:
          Extracted text content from the specified pages
      """
      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)}"
      
      # Warning for large page ranges
      if end_page - start_page > 50:
          warning = "Warning: Reading more than 50 pages at once may cause performance issues or errors.\n"
      else:
          warning = ""
      
      try:
          # Read PDF file
          with open(actual_path, 'rb') as file:
              pdf_content = file.read()
          
          # Extract text using the original function
          result = extract_text_from_pdf(pdf_content, start_page, end_page)
          return warning + result if warning else result
          
      except FileNotFoundError:
          return f"Error: File not found '{actual_path}'"
      except PermissionError:
          return f"Error: No permission to read file '{actual_path}'"
      except Exception as e:
          return f"Error reading PDF file: {str(e)}"