launch_editor · Godot MCP: Risk & Policy

WHAT IT DOES

What launch_editor does on Godot

AI agents invoke launch_editor 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.

PARAMETERS

Parameter	Type	Required	Description
`scene`	object	—	Scene to open on launch (e.g. "res://main.tscn")
`project_path`	object	—	Project path (default: current project root)

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why launch_editor needs a policy

This tool executes an external application (Godot editor) and can perform arbitrary operations within that editor environment depending on the project loaded. While not immediately destructive on its own, it grants execution capability over a complex game engine environment with access to file systems, scripts, and project resources.

From the tool's definition The tool 'launch_editor' launches the Godot editor with a project, which triggers an external process execution whose side effects depend on the project and editor state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

launch_editor Rate-limited

launch_editor 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.

View as policy code

policy.json

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

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Godot, so you can run agents against it safely.

FAQ

Questions about launch_editor

What does the launch_editor tool do? +

Launch Godot editor with project. 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.

What parameters does launch_editor accept? +

launch_editor accepts 2 parameters: scene, project_path. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on launch_editor? +

Register the Godot MCP server in PolicyLayer and add a rule for launch_editor: 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.

What risk level is launch_editor? +

launch_editor is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit launch_editor? +

Yes. Add a rate_limit block to the launch_editor 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.

How do I block launch_editor completely? +

Set action: deny in the PolicyLayer policy for launch_editor. 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.

What MCP server provides launch_editor? +

launch_editor 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.