AI agents use editor_undo to create or update resources in Godot — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Godot environment.
Undo reverses a previous write/modify operation in the editor, restoring prior state. It is a reversible state change (it can be re-done), making it Write rather than Destructive. Misuse has low blast radius as it only reverts the most recent action.
From the tool's definition Undo last editor action
Attacks that exploit this kind of access
Undo last editor action. It is categorised as a Write tool in the Godot MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Godot MCP server in PolicyLayer and add a rule for editor_undo: 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_undo is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the editor_undo 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_undo. 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_undo 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.
editor_undo is one line of Godot's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →