content_audit · Unreal MCP: Risk & Policy

WHAT IT DOES

What content_audit does on Unreal

AI agents invoke content_audit 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 content_audit needs a policy

This tool triggers execution of Unreal Engine's ContentAudit commandlet, which performs automated analysis across the project's asset database. While not destructive or modifying in itself, it executes a system operation whose effects (resource consumption, timing, computational load) depend on project size and asset complexity.

From the tool's definition Tool runs the ContentAudit commandlet, which is an external executable operation that scans and analyzes assets in Unreal Engine. The description explicitly states it 'runs' a commandlet, indicating execution of a built-in but non-trivial operation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

content_audit Rate-limited

content_audit 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": {
    "content_audit": {
      "limits": [
        {
          "counter": "content_audit_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 content_audit

What does the content_audit tool do? +

Run content audit to find costly or problematic assets (runs ContentAudit commandlet). 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 content_audit? +

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

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

Can I rate-limit content_audit? +

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

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

content_audit 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.