MCP Browser Agent

Instructions

Implementation Reference

• browser-use.py:210-210 (registration)

  Registers the execute_actions tool with the MCP server using the @mcp.tool() decorator.
  @mcp.tool()
• browser-use.py:212-230 (schema)

  Input schema and format description for the actions parameter via function docstring.
  """Execute actions from the planner state. Args: actions: A dictionary containing the planner state and actions in format: { "current_state": { "evaluation_previous_goal": str, "memory": str, "next_goal": str }, "action": [ {"action_name": {"param1": "value1"}}, ... ] } Note: If the page state changes (new elements appear) during action execution, the sequence will be interrupted and you'll need to get a new planner state. """
• browser-use.py:211-299 (handler)

  The core handler function that validates the input actions, converts them to action models using the Controller registry, executes each action sequentially while monitoring for DOM changes that could invalidate subsequent selectors, collects results, and returns a string summary of outcomes.
  async def execute_actions(actions: Dict[str, Any], ctx: Context) -> str: """Execute actions from the planner state. Args: actions: A dictionary containing the planner state and actions in format: { "current_state": { "evaluation_previous_goal": str, "memory": str, "next_goal": str }, "action": [ {"action_name": {"param1": "value1"}}, ... ] } Note: If the page state changes (new elements appear) during action execution, the sequence will be interrupted and you'll need to get a new planner state. """ browser_context = await browser_initialized_check() controller = ctx.request_context.lifespan_context["controller"] try: # Validate input format if not isinstance(actions, dict) or "action" not in actions: return "Error: Actions must be a dictionary containing 'action' list" action_list = actions["action"] if not action_list: return "No actions to execute" # Get initial state for DOM change detection initial_state = await browser_context.get_state() initial_path_hashes = set(e.hash.branch_path_hash for e in initial_state.selector_map.values()) # Convert system prompt action format to action models action_models = [] for action_dict in action_list: if not isinstance(action_dict, dict) or len(action_dict) != 1: return "Error: Each action must be a dictionary with exactly one key-value pair" action_name = list(action_dict.keys())[0] params = action_dict[action_name] # Create action model using the controller's registry action_model = controller.registry.create_action_model()(**{action_name: params}) action_models.append(action_model) # Execute actions one by one to check for DOM changes results = [] for i, action_model in enumerate(action_models): # Execute single action result = await controller.act(action_model, browser_context) results.append(result) # Check if this action requires element interaction requires_elements = any(param in str(action_model) for param in ["index", "xpath"]) # If not the last action and next action might need elements, check for DOM changes if i < len(action_models) - 1: new_state = await browser_context.get_state() new_path_hashes = set(e.hash.branch_path_hash for e in new_state.selector_map.values()) # If DOM changed and next action needs elements, break sequence if requires_elements and not new_path_hashes.issubset(initial_path_hashes): msg = f"Page state changed after action {i + 1}/{len(action_models)}. Please get new planner state before continuing." logger.info(msg) results.append(ActionResult(extracted_content=msg, include_in_memory=True)) break # Stop if there was an error if result.error: break # Process results output = [] for result in results: if result.extracted_content: output.append(result.extracted_content) elif result.error: output.append(f"Error: {result.error}") else: output.append("Action executed successfully") return "\n".join(output) except Exception as e: logger.error(f"Error executing actions: {str(e)}") return f"Error executing actions: {str(e)}"