wait_for_text · Poof MCP: Risk & Policy

WHAT IT DOES

What wait_for_text does on Poof

AI agents invoke wait_for_text 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 wait_for_text needs a policy

Although 'wait_for_text' itself is a read-only observation function, it operates within an Execute context: the server's stated purpose is to 'control' Terminal.app and enable agents to send keystrokes and type text. This tool is a dependency for executing complex terminal workflows—an agent would use 'send_keystrokes' to run a command, then 'wait_for_text' to confirm execution, then proceed conditionally.

From the tool's definition The tool 'wait_for_text' is part of a server that 'enables AI agents to control the macOS Terminal.app' and allows agents to 'send keystrokes, type text, and capture screen output.' This tool observes terminal output, and when combined with sibling tools like…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

wait_for_text Rate-limited

wait_for_text 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": {
    "wait_for_text": {
      "limits": [
        {
          "counter": "wait_for_text_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 wait_for_text

What does the wait_for_text tool do? +

Wait for text to appear on screen (5s default timeout). 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 wait_for_text? +

Register the Poof MCP server in PolicyLayer and add a rule for wait_for_text: 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 wait_for_text? +

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

Can I rate-limit wait_for_text? +

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

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

wait_for_text 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.