AI agents invoke editor_toggle_snap 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.
Toggling the 3D snap mode in the Godot editor is an editor state change that triggers an external operation (modifying editor behavior/settings). It doesn't read data, write persistent content, or destroy anything, but it does change the active editor mode/state, making Execute the most appropriate category. The blast radius is low as it only affects snap behavior in the 3D editor.
From the tool's definition Toggle 3D snap mode
Attacks that exploit this kind of access
Toggle 3D snap mode. 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.
Register the Godot MCP server in PolicyLayer and add a rule for editor_toggle_snap: 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_toggle_snap 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_toggle_snap 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_toggle_snap. 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_toggle_snap 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_toggle_snap 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 →