resize_terminal · Poof MCP: Risk & Policy

WHAT IT DOES

What resize_terminal does on Poof

AI agents invoke resize_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 resize_terminal needs a policy

Resizing a terminal window is an Execute-level action as it triggers an external operation (AppleScript command to Terminal.app) that changes window state. It is not purely a Read or Write of data, but the blast radius is low since resizing only affects the visual layout of the terminal, not its data or running processes.

From the tool's definition 'Resize the terminal' — modifies the terminal window dimensions via AppleScript control of Terminal.app

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

resize_terminal Rate-limited

resize_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": {
    "resize_terminal": {
      "limits": [
        {
          "counter": "resize_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 resize_terminal

What does the resize_terminal tool do? +

Resize the terminal. 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 resize_terminal? +

Register the Poof MCP server in PolicyLayer and add a rule for resize_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 resize_terminal? +

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

Can I rate-limit resize_terminal? +

Yes. Add a rate_limit block to the resize_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 resize_terminal completely? +

Set action: deny in the PolicyLayer policy for resize_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 resize_terminal? +

resize_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.