AI agents invoke stop_project to trigger actions in Godot MCP. 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 triggers an external operation (halting a running game engine project) whose effects depend on runtime state. It is not a data read/query (Read), not a reversible creation/modification (Write), and not irreversible data deletion (Destructive). It is Execute-class because it controls process lifecycle.
From the tool's definition Tool name 'stop_project' and description 'Stop the currently running Godot project' indicate termination of an external process/operation.
Attacks that exploit this kind of access
Stop the currently running Godot project. It is categorised as a Execute tool in the Godot MCP 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 stop_project: 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. Nothing to install.
stop_project 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_project 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_project. 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_project is provided by the Godot MCP server (jamesdowzard/godot-mcp). 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 →