autopilot · LocalAnt MCP: Risk & Policy

WHAT IT DOES

What autopilot does on LocalAnt

AI agents invoke autopilot to trigger actions in LocalAnt. 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 needs a policy

Delegating arbitrary natural-language tasks to a local agent that can run shell commands, manage files, and automate browsers is essentially an unrestricted Execute capability. The blast radius is critical because a misused instruction could trigger any downstream tool on the server, including destructive or financial operations, all through a single natural-language prompt.

From the tool's definition Delegate a natural-language local task to LocalAnt — the server description states it 'lets ChatGPT control your PC through approved, permissioned tools for shell commands, file management, coding agents, browser automation, and more'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

autopilot Rate-limited

autopilot 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": {
      "limits": [
        {
          "counter": "autopilot_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 LocalAnt, so you can run agents against it safely.

FAQ

Questions about autopilot

What does the autopilot tool do? +

Delegate a natural-language local task to LocalAnt. It is categorised as a Execute tool in the LocalAnt 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? +

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

What risk level is autopilot? +

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

Can I rate-limit autopilot? +

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

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

autopilot is provided by the LocalAnt MCP server (yuga-hashimoto/localant). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.