stop_server · Llauncher MCP: Risk & Policy

WHAT IT DOES

What stop_server does on Llauncher

AI agents invoke stop_server to trigger actions in Llauncher. 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 stop_server needs a policy

This tool executes a command to halt a running inference server instance. While not destructive (the server can be restarted), it is an Execute action because it triggers an external operation (process termination) whose effects are immediate and depend on the port argument.

From the tool's definition Tool description states 'Stop whatever is running on this port', indicating it executes an action that terminates a running process/service. The idempotent nature confirms it performs a real operation, not a read.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

stop_server Rate-limited

stop_server 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": {
    "stop_server": {
      "limits": [
        {
          "counter": "stop_server_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 Llauncher, so you can run agents against it safely.

FAQ

Questions about stop_server

What does the stop_server tool do? +

Stop whatever is running on this port. Idempotent:. It is categorised as a Execute tool in the Llauncher MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on stop_server? +

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

What risk level is stop_server? +

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

Can I rate-limit stop_server? +

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

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

stop_server is provided by the Llauncher MCP server (shanevcantwell/llauncher). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// THE FULL RECORD

stop_server is one line of Llauncher's registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →