execute_scene_script

What execute_scene_script does on Cocos

AI agents invoke execute_scene_script to trigger actions in Cocos. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

Why execute_scene_script is rated High

This tool executes scene script methods, which are external operations whose effects depend on the arguments passed. Scene scripts can perform any action within the game/editor context, including modifying nodes, components, physics, rendering, and other systems. While not inherently destructive or financial, it represents a classic Execute risk: triggering code with unpredictable side effects.

From the tool's definition execute_scene_script: Execute scene script method. This tool directly runs code within the scene context, triggering arbitrary scene script methods with effects dependent on the arguments provided.

The rule that runs execute_scene_script safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Cocos, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For execute_scene_script, this is the rule to start with:

{
  "version": "1",
  "default": "deny",
  "tools": {
    "execute_scene_script": {
      "limits": [
        {
          "counter": "execute_scene_script_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

Questions about execute_scene_script