run_game · Godot Sentinel MCP: Risk & Policy

WHAT IT DOES

What run_game does on Godot Sentinel MCP

AI agents invoke run_game to trigger actions in Godot Sentinel 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.

WHY IT NEEDS A POLICY

Why run_game needs a policy

This tool triggers execution of game code with external side effects (rendering, input handling, game state changes, potential file I/O, network calls defined in the game). While not destructive on its own, the blast radius includes unintended game state modifications, resource consumption, or triggering of game-defined side effects.

From the tool's definition Tool launches the Godot game runtime ('Launch the Godot game'), which executes arbitrary game code and external operations whose effects depend on runtime arguments (scene override parameter).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_game Rate-limited

run_game stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_game": {
      "limits": [
        {
          "counter": "run_game_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Godot Sentinel MCP, so you can run agents against it safely.

FAQ

Questions about run_game

What does the run_game tool do? +

Launch the Godot game with optional scene override. It is categorised as a Execute tool in the Godot Sentinel MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_game? +

Register the Godot Sentinel MCP server in PolicyLayer and add a rule for run_game: 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 Sentinel MCP. Nothing to install.

What risk level is run_game? +

run_game is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit run_game? +

Yes. Add a rate_limit block to the run_game 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.

How do I block run_game completely? +

Set action: deny in the PolicyLayer policy for run_game. 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.

What MCP server provides run_game? +

run_game is provided by the Godot Sentinel MCP server (snack-jpg/godot-sentinel-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.