Run a specific scene in the Godot project (non-headless, will open a window).
AI agents invoke godot_run_scene to trigger actions in Godot MCP Server. 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.
This tool executes code by launching a Godot scene, which involves instantiating nodes, running their _ready() and _process() callbacks, and potentially executing any game logic defined in that scene.
From the tool's definition Tool description states it will "Run a specific scene in the Godot project (non-headless, will open a window)." The term "run" combined with opening a window indicates execution of arbitrary game code within the Godot engine.
Attacks that exploit this kind of access
Run a specific scene in the Godot project (non-headless, will open a window). It is categorised as a Execute tool in the Godot MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Godot MCP Server MCP server in PolicyLayer and add a rule for godot_run_scene: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Godot MCP Server. Nothing to install.
godot_run_scene is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the godot_run_scene rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for godot_run_scene. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
godot_run_scene is provided by the Godot MCP Server MCP server (struktured-labs/godot-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →