execute_actions
Run planner-based actions in the MCP Browser Agent to automate web interactions, including navigation and element manipulation, while adapting to dynamic page state changes.
Instructions
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.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| actions | Yes |
Input Schema (JSON Schema)
{
"properties": {
"actions": {
"title": "Actions",
"type": "object"
}
},
"required": [
"actions"
],
"title": "execute_actionsArguments",
"type": "object"
}