execute_commands
Execute and manage Revit commands via JSON-RPC 2.0, enabling batch processing, toggling feature panels, and robust error handling for automated model interactions.
Instructions
执行指定的功能命令，遵循JSON-RPC 2.0规范。 mcp_tool使用时params不要有任何注释信息
特性:
支持批量执行多个功能命令
可以指定是添加还是移除功能面板
自动查找并执行匹配名称的功能
完善的错误处理机制
参数: ctx (Context): FastMCP上下文对象 method (str): JSON-RPC方法名，默认为"ExecuteCommands" params (List[Dict]): 命令参数列表，每个字典包含: - name (str): 要执行的功能名称 - add (bool): True表示添加功能面板，False表示移除功能面板
返回: dict: JSON-RPC 2.0格式的响应，结构为: 成功时: { "jsonrpc": "2.0", "result": [ { "name": "AI助手", "description": "使用DeepSeek直接操作Revit,会员用户抢先体验", "tooltip": "关注公众号获取最新功能消息(F1获取帮助)" }, { "name": "AI代码转换", "description": "AI生成的代码功能尝试转换为Revit可用功能,会员用户抢先体验~", "tooltip": "关注公众号获取最新功能消息(F1获取帮助)" }, ... ], "id": request_id } 失败时: { "jsonrpc": "2.0", "error": { "code": int, "message": str, "data": any }, "id": request_id }
示例: # 添加功能面板 response = execute_command(ctx, params=[ {"name": "AI助手", "add": True}, {"name": "AI代码转换", "add": True} ])
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| method | No | ExecuteCommands | |
| params | No |
Implementation Reference
- xml_revit_mcp/server.py:50-55 (registration)List of general tools including the execute_commands function referenceGENERAL_TOOLS = [ get_commands, execute_commands, call_func, find_elements, update_elements, delete_elements, parameter_elements, get_locations, move_elements, show_elements, active_view, get_selected_elements, link_dwg_and_activate_view, get_view_data ]
- xml_revit_mcp/server.py:144-146 (registration)Registration of general tools by applying the FastMCP tool decorator to each function in GENERAL_TOOLS, including execute_commands# 注册通用工具 for tool in GENERAL_TOOLS: server.tool()(tool)
- xml_revit_mcp/server.py:16-16 (registration)Import statement that brings in the tool functions, including execute_commands, into scopefrom .tools import *
- xml_revit_mcp/server.py:58-95 (helper)Function to get or create the persistent RevitConnection used by tools to send commandsdef get_revit_connection() -> RevitConnection: """ 获取或创建持久的Revit连接 返回: RevitConnection: 与Revit的连接对象 异常: Exception: 连接失败时抛出 """ global _connection, _enabled if _connection is not None: try: # 测试连接是否有效 result = _connection.send_command("get_polyhaven_status") _enabled = result.get("enabled", False) return _connection except Exception as e: logger.warning(f"现有连接已失效: {str(e)}") try: _connection.disconnect() except: pass _connection = None # 创建新连接 if _connection is None: _connection = RevitConnection(host="localhost", port=_port) if not _connection.connect(): logger.error("无法连接到Revit") _connection = None raise Exception( "无法连接到Revit。请确保Revit插件正在运行。") logger.info("已创建新的持久连接到Revit") return _connection
- Core method in RevitConnection that sends a command (e.g., 'execute_commands') with parameters to the Revit plugin via TCP socket and returns the result; this is the underlying implementation executed by the MCP tool handlersdef send_command(self, command_type: str, params: Union[Dict[str, Any], List[Dict[str, Any]]] = None) -> Dict[ str, Any]: """ 向Revit发送命令并返回响应 参数: command_type (str): 命令类型 params (Dict[str, Any] 或 List[Dict[str, Any]]): 命令参数 返回: Dict[str, Any]: 命令响应 异常: ConnectionError: 连接错误 TimeoutError: 请求超时 ValueError: 参数或响应无效 Exception: 其他错误 """ # 确保连接 if not self.sock and not self.connect(): raise ConnectionError("无法连接到Revit") try: logger.info(f"发送命令: {command_type}") logger.debug(f"命令参数: {params}") # 导入并创建请求对象 from .rpc import JsonRPCRequest, JsonRPCResponse command = JsonRPCRequest(method=command_type, params=params) command_json = json.dumps(command.__dict__) # 发送命令 self.sock.sendall(command_json.encode('utf-8')) logger.debug("命令已发送，等待响应...") # 使用 receive_full_response 接收完整数据流 response_data = self.receive_full_response() logger.debug(f"已接收 {len(response_data)} 字节数据") # 解析响应 try: response_dict = json.loads(response_data.decode('utf-8')) response = JsonRPCResponse( id=response_dict.get("id"), result=response_dict.get("result"), error=response_dict.get("error") ) except json.JSONDecodeError as e: logger.error(f"无法解析Revit响应: {str(e)}") if response_data: logger.error(f"原始响应 (前200字节): {response_data[:200]}") raise ValueError(f"无效的Revit响应: {str(e)}") # 处理错误 if response.error: error_message = response.error.get("message", "未知错误") error_code = response.error.get("code", -1) error_data = response.error.get("data") logger.error(f"Revit错误 (代码: {error_code}): {error_message}") if error_data: logger.error(f"错误数据: {error_data}") raise Exception(f"Revit错误: {error_message}") return response.result or {}