Stop the currently running game.
AI agents invoke stop_scene to trigger actions in Godot MCP Server. 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.
This tool executes a command that triggers an external process state change—stopping a running game session. While not destructive to data or financial in nature, it qualifies as Execute because it invokes a controlled operation in the Godot runtime.
From the tool's definition Tool name 'stop_scene' and description 'Stop the currently running game' indicate triggering an external operation (halting game execution) whose effects depend on the state of the Godot editor.
Attacks that exploit this kind of access
Stop the currently running game. It is categorised as a Execute tool in the Godot MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Godot MCP Server MCP server in PolicyLayer and add a rule for stop_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 MCP Server. Nothing to install.
stop_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 stop_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 stop_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.
stop_scene is provided by the Godot MCP Server MCP server (neondeex/godotmcp-pro-free-client). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →