shell_stop · LocalAnt MCP: Risk & Policy

WHAT IT DOES

What shell_stop does on LocalAnt

AI agents invoke shell_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 shell_stop needs a policy

Stopping a background process is an Execute action because it runs/triggers an operation (process termination) whose effects depend on which process is targeted. While not permanently destructive (the process can be restarted), it causes immediate service disruption and falls short of Destructive category.

From the tool's definition Tool name is 'shell_stop' and description states it will 'Stop a tracked background process.' This performs process termination, which is an executable action that triggers external OS-level operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

shell_stop Rate-limited

shell_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": {
    "shell_stop": {
      "limits": [
        {
          "counter": "shell_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 shell_stop

What does the shell_stop tool do? +

Stop a tracked background process. 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 shell_stop? +

Register the LocalAnt MCP server in PolicyLayer and add a rule for shell_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 shell_stop? +

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

Can I rate-limit shell_stop? +

Yes. Add a rate_limit block to the shell_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 shell_stop completely? +

Set action: deny in the PolicyLayer policy for shell_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 shell_stop? +

shell_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.