stop_scrub · Livepilot MCP: Risk & Policy

WHAT IT DOES

What stop_scrub does on Livepilot

AI agents invoke stop_scrub to trigger actions in Livepilot. 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 stop_scrub needs a policy

stop_scrub triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

stop_scrub Rate-limited

stop_scrub 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": {
    "stop_scrub": {
      "limits": [
        {
          "counter": "stop_scrub_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 Livepilot, so you can run agents against it safely.

FAQ

Questions about stop_scrub

What does the stop_scrub tool do? +

Stop scrubbing a clip. Call after scrub_clip to stop preview. It is categorised as a Execute tool in the Livepilot MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on stop_scrub? +

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

What risk level is stop_scrub? +

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

Can I rate-limit stop_scrub? +

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

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

stop_scrub is provided by the Livepilot MCP server (livepilot). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.