run_gauntlet · Unreal MCP: Risk & Policy

WHAT IT DOES

What run_gauntlet does on Unreal

AI agents invoke run_gauntlet to trigger actions in Unreal. 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_gauntlet needs a policy

The tool triggers execution of arbitrary test suites (Gauntlet tests) within a live Unreal Engine game instance via the Unreal Automation Tool (UAT). This is a code execution action whose effects depend entirely on what tests are specified—tests could interact with game state, modify assets, access sensitive data, or cause unpredictable side effects.

From the tool's definition Tool description explicitly states 'Launch a Gauntlet test session via UAT' and 'Runs tests in a full game instance.' These clearly indicate execution of test code within a game runtime environment.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_gauntlet Rate-limited

run_gauntlet 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_gauntlet": {
      "limits": [
        {
          "counter": "run_gauntlet_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 Unreal, so you can run agents against it safely.

FAQ

Questions about run_gauntlet

What does the run_gauntlet tool do? +

Launch a Gauntlet test session via UAT. Runs tests in a full game instance. It is categorised as a Execute tool in the Unreal 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_gauntlet? +

Register the Unreal MCP server in PolicyLayer and add a rule for run_gauntlet: 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 Unreal. Nothing to install.

What risk level is run_gauntlet? +

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

Can I rate-limit run_gauntlet? +

Yes. Add a rate_limit block to the run_gauntlet 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_gauntlet completely? +

Set action: deny in the PolicyLayer policy for run_gauntlet. 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_gauntlet? +

run_gauntlet is provided by the Unreal MCP server (sam-david/unreal-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.