autopilot_disable · Claude Flow MCP: Risk & Policy

WHAT IT DOES

What autopilot_disable does on Claude Flow

AI agents invoke autopilot_disable to trigger actions in Claude Flow. 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 autopilot_disable needs a policy

Disabling autopilot modifies the execution control plane of a multi-agent orchestration system, potentially halting progress on long-running tasks and allowing agents to terminate mid-work. This is an operational state change with significant side effects on running workloads.

From the tool's definition 'Disable autopilot. Agents will be allowed to stop even if tasks remain.' — changes the operational mode of an AI orchestration system, affecting agent lifecycle and task execution behavior.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

autopilot_disable Rate-limited

autopilot_disable 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": {
    "autopilot_disable": {
      "limits": [
        {
          "counter": "autopilot_disable_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 Claude Flow, so you can run agents against it safely.

FAQ

Questions about autopilot_disable

What does the autopilot_disable tool do? +

Disable autopilot. Agents will be allowed to stop even if tasks remain. Use when running long-horizon goals that should resume automatically across sessions — Claude Code has no native autonomous-loop scheduler. Pair with autopilot_enable + a goal description, then let cron fires advance the work. For interactive single-task sessions, native Task is fine. It is categorised as a Execute tool in the Claude Flow MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on autopilot_disable? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for autopilot_disable: 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 Claude Flow. Nothing to install.

What risk level is autopilot_disable? +

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

Can I rate-limit autopilot_disable? +

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

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

autopilot_disable is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.