tunnel_start · LocalAnt MCP: Risk & Policy

WHAT IT DOES

What tunnel_start does on LocalAnt

AI agents invoke tunnel_start 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 tunnel_start needs a policy

This tool triggers an external operation (starting a public tunnel) whose effects are significant and depend on gateway configuration. It enables network exposure of the LocalAnt gateway, potentially allowing remote access to the PC control capabilities. This is an Execute action because it initiates a process/service with real-world side effects, but not Destructive (reversible via tunnel_stop) and not Financial.

From the tool's definition Tool name 'tunnel_start' combined with description 'Start the public tunnel on the live gateway port' indicates initiation of a network tunnel that exposes a local service to the public internet.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

tunnel_start Rate-limited

tunnel_start 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": {
    "tunnel_start": {
      "limits": [
        {
          "counter": "tunnel_start_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 tunnel_start

What does the tunnel_start tool do? +

Start the public tunnel on the live gateway port. 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 tunnel_start? +

Register the LocalAnt MCP server in PolicyLayer and add a rule for tunnel_start: 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 tunnel_start? +

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

Can I rate-limit tunnel_start? +

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

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

tunnel_start 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.