restart_terminal · Poof MCP: Risk & Policy

WHAT IT DOES

What restart_terminal does on Poof

AI agents invoke restart_terminal to trigger actions in Poof. 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 restart_terminal needs a policy

This tool triggers an external operation (terminal restart) that can execute arbitrary commands on the macOS system. While not destructive in the sense of permanent deletion, restarting the terminal with a new command is an execution capability that could be abused to run harmful scripts or commands.

From the tool's definition Tool description states 'Restart the terminal (optionally with a new command)' and server description indicates the MCP server 'enables AI agents to control the macOS Terminal.app' with AppleScript.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

restart_terminal Rate-limited

restart_terminal 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": {
    "restart_terminal": {
      "limits": [
        {
          "counter": "restart_terminal_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 Poof, so you can run agents against it safely.

FAQ

Questions about restart_terminal

What does the restart_terminal tool do? +

Restart the terminal (optionally with a new command). It is categorised as a Execute tool in the Poof MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on restart_terminal? +

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

What risk level is restart_terminal? +

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

Can I rate-limit restart_terminal? +

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

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

restart_terminal is provided by the Poof MCP server (mattapperson/poof-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.