run_project · Godot MCP: Risk & Policy

WHAT IT DOES

What run_project does on Godot MCP

AI agents invoke run_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.

WHY IT NEEDS A POLICY

Why run_project needs a policy

This tool triggers execution of external code (the Godot game engine project), whose behavior and side effects depend entirely on the project's implementation. While it captures output rather than modifying files directly, it executes code whose effects could range from rendering/audio operations to network calls or file manipulation depending on what the project contains.

From the tool's definition Tool name 'run_project' combined with description 'Run the Godot project and capture output' indicates execution of arbitrary game engine code. The sibling context (launch_editor, create_scene, manage resources) confirms this is a runtime execution tool.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_project Rate-limited

run_project 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_project": {
      "limits": [
        {
          "counter": "run_project_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 MCP, so you can run agents against it safely.

FAQ

Questions about run_project

What does the run_project tool do? +

Run the Godot project and capture output. 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.

How do I enforce a policy on run_project? +

Register the Godot MCP server in PolicyLayer and add a rule for run_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.

What risk level is run_project? +

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

Can I rate-limit run_project? +

Yes. Add a rate_limit block to the run_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.

How do I block run_project completely? +

Set action: deny in the PolicyLayer policy for run_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.

What MCP server provides run_project? +

run_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.