render_and_audit · Orpheus MCP: Risk & Policy

WHAT IT DOES

What render_and_audit does on Orpheus

AI agents invoke render_and_audit to trigger actions in Orpheus. 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 render_and_audit needs a policy

This tool actively renders (executes) a music project in REAPER and then performs audio measurements. Rendering is an external operation that produces output files and triggers processing pipelines, going beyond a simple read. Since it combines execution of a render with measurement, it falls under Execute.

From the tool's definition 'Render' — triggers an external rendering operation on the REAPER project; 'measure LUFS/spectrum in one call so the agent self-checks' — executes a multi-step process combining rendering and audio analysis

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

render_and_audit Rate-limited

render_and_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": {
    "render_and_audit": {
      "limits": [
        {
          "counter": "render_and_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 Orpheus, so you can run agents against it safely.

FAQ

Questions about render_and_audit

What does the render_and_audit tool do? +

Render, then measure LUFS/spectrum in one call so the agent self-checks. It is categorised as a Execute tool in the Orpheus MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on render_and_audit? +

Register the Orpheus MCP server in PolicyLayer and add a rule for render_and_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 Orpheus. Nothing to install.

What risk level is render_and_audit? +

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

Can I rate-limit render_and_audit? +

Yes. Add a rate_limit block to the render_and_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 render_and_audit completely? +

Set action: deny in the PolicyLayer policy for render_and_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 render_and_audit? +

render_and_audit is provided by the Orpheus MCP server (mal0ware/orpheus). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.