ligolo_tunnel_stop · Ligolo-ng MCP Server MCP: Risk & Policy

WHAT IT DOES

What ligolo_tunnel_stop does on Ligolo-ng MCP Server

AI agents invoke ligolo_tunnel_stop to trigger actions in Ligolo-ng MCP Server. 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 ligolo_tunnel_stop needs a policy

This tool executes a command to stop a network tunnel on a remote system (Kali Linux via SSH). While not destructive (the tunnel can be restarted), it is Execute-class because it triggers an operation external to the MCP server with real-time effects on network infrastructure. Misuse by an AI agent could disrupt active security assessments or authorized penetration testing activities, warranting high severity.

From the tool's definition Stop the active tunnel — an action that terminates an active network tunnel used for pivoting during security assessments. The tool directly triggers an external operation (tunnel termination) whose effects are immediate and depend on the current tunnel state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ligolo_tunnel_stop Rate-limited

ligolo_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": {
    "ligolo_tunnel_stop": {
      "limits": [
        {
          "counter": "ligolo_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 Ligolo-ng MCP Server, so you can run agents against it safely.

FAQ

Questions about ligolo_tunnel_stop

What does the ligolo_tunnel_stop tool do? +

Stop the active tunnel. It is categorised as a Execute tool in the Ligolo-ng MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on ligolo_tunnel_stop? +

Register the Ligolo-ng MCP Server MCP server in PolicyLayer and add a rule for ligolo_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 Ligolo-ng MCP Server. Nothing to install.

What risk level is ligolo_tunnel_stop? +

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

Can I rate-limit ligolo_tunnel_stop? +

Yes. Add a rate_limit block to the ligolo_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 ligolo_tunnel_stop completely? +

Set action: deny in the PolicyLayer policy for ligolo_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 ligolo_tunnel_stop? +

ligolo_tunnel_stop is provided by the Ligolo-ng MCP Server MCP server (schwarztim/sec-ligolo-ng-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.