PDF Tools MCP Server

Instructions

Args:
    search_id: Search session ID from previous search

Returns:
    Previous page of search results or error message

Implementation Reference

• pdf_tools_mcp/server.py:749-788 (handler)

  The handler function for the 'search_pdf_prev_page' tool, which navigates to the previous page of search results for a given session ID.

  @mcp.tool()
  async def search_pdf_prev_page(search_id: str) -> str:
      """Get previous page of search results.
      
      Args:
          search_id: Search session ID from previous search
      
      Returns:
          Previous page of search results or error message
      """
      with cache_lock:
          session = search_sessions.get(search_id)
          if not session:
              return f"Error: Search session '{search_id}' not found or expired"
          
          session.last_accessed = datetime.now()
          
          if session.current_page <= 1:
              return f"Already on first page (1)"
          
          session.current_page -= 1
          
          start_idx = (session.current_page - 1) * session.page_size
          end_idx = min(start_idx + session.page_size, len(session.results))
          current_results = session.results[start_idx:end_idx]
          
          total_pages = (len(session.results) + session.page_size - 1) // session.page_size
          
          result = f"Search ID: {search_id}\n"
          result += f"Pattern: {session.pattern}\n"
          result += f"Total matches: {session.total_results}\n"
          result += f"Page: {session.current_page}/{total_pages}\n\n"
          
          for i, match in enumerate(current_results, 1):
              result += f"Match {start_idx + i}:\n"
              result += f"  Page: {match.page_number}\n"
              result += f"  Text: \"{match.text}\"\n"
              result += f"  Context: ...{match.context_before}[{match.text}]{match.context_after}...\n\n"
          
          return result