AI agents use editor_save 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.
The tool creates or modifies data by saving the current scene, which is a reversible write operation. Severity is medium because saving a scene can overwrite existing work (loss of prior state), but the action is reversible through undo/version control and does not destroy data permanently or execute arbitrary code.
From the tool's definition Tool name 'editor_save' and description 'Save current scene in editor' indicate the tool modifies and persists data (the scene state) to storage.
Attacks that exploit this kind of access
Save current scene in editor. 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_save: 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_save 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_save 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_save. 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_save 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_save 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 →