autopilot_enable · Claude Flow MCP: Risk & Policy

WHAT IT DOES

What autopilot_enable does on Claude Flow

AI agents invoke autopilot_enable 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_enable needs a policy

This tool enables an autonomous execution loop that continuously re-engages agents to complete tasks across sessions, triggered by cron. It executes ongoing agent operations without direct human oversight per cycle. The blast radius is high because enabling this could cause uncontrolled, persistent automated actions (spawning agents, running tasks) on long-horizon goals with no native stop mechanism per session.

From the tool's definition Agents will be re-engaged when tasks remain incomplete... let cron fires advance the work... autonomous-loop scheduler

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

autopilot_enable Rate-limited

autopilot_enable 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_enable": {
      "limits": [
        {
          "counter": "autopilot_enable_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_enable

What does the autopilot_enable tool do? +

Enable autopilot persistent completion. Agents will be re-engaged when tasks remain incomplete. 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_enable? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for autopilot_enable: 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_enable? +

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

Can I rate-limit autopilot_enable? +

Yes. Add a rate_limit block to the autopilot_enable 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_enable completely? +

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

autopilot_enable 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.