MindManager MCP Server

Instructions

Extracts grounding information (central topic, selected subtopics) from the mindmap.

Args:
    mode (str): Detail level ('full', 'content', 'text'). Defaults to 'full'.
    turbo_mode (bool): Enable turbo mode (text only). Defaults to False.

Returns:
    Union[List[str], Dict[str, str]]: A list containing [top_most_topic, subtopics_string] or error dictionary.

Implementation Reference

• mindm_mcp/server.py:253-277 (handler)

  The primary handler for the 'get_grounding_information' MCP tool. Registered via @mcp.tool() decorator. Handles parameters, calls helper function, serializes output, and manages errors.

  @mcp.tool()
  async def get_grounding_information(
      mode: str = 'full',
      turbo_mode: bool = False
  ) -> Union[List[str], Dict[str, str]]:
      """
      Extracts grounding information (central topic, selected subtopics) from the mindmap.
  
      Args:
          mode (str): Detail level ('full', 'content', 'text'). Defaults to 'full'.
          turbo_mode (bool): Enable turbo mode (text only). Defaults to False.
  
      Returns:
          Union[List[str], Dict[str, str]]: A list containing [top_most_topic, subtopics_string] or error dictionary.
      """
      try:
          print("Calling get_grounding_information()", file=sys.stderr)
          top_most, subtopics_str = _get_grounding_information(mode=mode, turbo_mode=turbo_mode)
          print(f"get_grounding_information() returned: top='{top_most}', subtopics='{subtopics_str}'", file=sys.stderr)
          return [top_most, subtopics_str] # Return as list for JSON
      except Exception as e:
          # This function doesn't directly call MindManager, so errors are less likely external
          print(f"ERROR in get_grounding_information: {e}", file=sys.stderr)
          return {"error": "Internal Error", "message": f"Failed to get grounding information: {e}"}

• mindm_mcp/server.py:110-115 (helper)

  Supporting helper function that creates a MindmapDocument instance, retrieves the mindmap and selection, and calls the underlying get_grounding_information method on the document.

  def _get_grounding_information(mode='text', turbo_mode=True):
      document = _get_document_instance(turbo_mode=turbo_mode)
      if document.get_mindmap(mode=mode):
          document.get_selection()
          return document.get_grounding_information()
      return None

• mindm_mcp/server.py:253-253 (registration)

  The @mcp.tool() decorator registers the get_grounding_information function as an MCP tool.

  @mcp.tool()