tunnel_stop · LocalAnt MCP: Risk & Policy

WHAT IT DOES

What tunnel_stop does on LocalAnt

AI agents invoke tunnel_stop 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_stop needs a policy

Stopping a tunnel is an Execute action—it triggers an external operation (terminating a tunnel process) whose effects depend on which tunnel is running. It is not Read (no data retrieval), Write (not creating/modifying reversible data), Destructive (the tunnel can be restarted), or Financial. Severity is medium because stopping a tunnel disrupts connectivity but does not destroy data or cause financial harm.

From the tool's definition Tool name 'tunnel_stop' and description 'Stop the public tunnel' indicate termination of an active network tunnel service. This is an operational action that affects system state and network connectivity.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

tunnel_stop Rate-limited

tunnel_stop 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_stop": {
      "limits": [
        {
          "counter": "tunnel_stop_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_stop

What does the tunnel_stop tool do? +

Stop the public tunnel. 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_stop? +

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

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

Can I rate-limit tunnel_stop? +

Yes. Add a rate_limit block to the tunnel_stop 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_stop completely? +

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

tunnel_stop 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.