editor_run_specific_scene
Run a specific scene (not just main).
This record as markdown: /tools/yanhuifair-godot-mcp/editor-run-specific-scene.md
What editor_run_specific_scene does on Godot
AI agents invoke editor_run_specific_scene to trigger actions in Godot. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
scene | string | Yes | Scene path to run (e.g. "res://scenes/level1.tscn") |
Parameters from the server's own tool schema.
Why editor_run_specific_scene is rated High
This tool triggers execution of external code (scene scripts, node _ready() functions, physics, input handlers, etc.) within the Godot engine. The blast radius is high because a malicious scene could access the filesystem, network, modify project state, or cause engine crashes. While not directly destructive (reversible by stopping execution), it is fundamentally an Execute action that runs untrusted logic.
From the tool's definition 'Run a specific scene' indicates execution of arbitrary Godot scenes, which can contain user code, node logic, and side effects dependent on scene content.
Attacks that exploit this kind of access
The rule that runs editor_run_specific_scene safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Godot, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For editor_run_specific_scene, this is the rule to start with:
editor_run_specific_scene stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Godot, apply this rule, and every editor_run_specific_scene call is checked against it from then on.
Questions about editor_run_specific_scene
Run a specific scene (not just main). It is categorised as a Execute tool in the Godot MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
editor_run_specific_scene accepts 1 parameter: scene. Required: scene. The full parameter table on this page comes from the server's own tool schema.
Register the Godot MCP server in PolicyLayer and add a rule for editor_run_specific_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. Nothing to install.
editor_run_specific_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 editor_run_specific_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 editor_run_specific_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.
editor_run_specific_scene is provided by the Godot MCP server (@yanhuifair/godot-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Godot, and thousands of servers like it.
Across the catalogue