build_cook_run · Unreal MCP: Risk & Policy

WHAT IT DOES

What build_cook_run does on Unreal

AI agents invoke build_cook_run 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 build_cook_run needs a policy

This tool triggers a complete build-cook-run pipeline in Unreal Engine, which compiles code, processes assets, stages files, packages the project, and can deploy/run the result. While not destructive (data remains intact), it executes external operations whose effects depend on configuration arguments and can modify the local filesystem and potentially remote systems if deployment is triggered.

From the tool's definition Tool performs 'Full BuildCookRun pipeline — build, cook, stage, package, and optionally deploy/run' which executes a complex multi-stage compilation and deployment process with external effects.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

build_cook_run Rate-limited

build_cook_run 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": {
    "build_cook_run": {
      "limits": [
        {
          "counter": "build_cook_run_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 build_cook_run

What does the build_cook_run tool do? +

Full BuildCookRun pipeline — build, cook, stage, package, and optionally deploy/run. This is the primary command for packaging a project. 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 build_cook_run? +

Register the Unreal MCP server in PolicyLayer and add a rule for build_cook_run: 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 build_cook_run? +

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

Can I rate-limit build_cook_run? +

Yes. Add a rate_limit block to the build_cook_run 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 build_cook_run completely? +

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

build_cook_run 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.