wait_for_url · MacWright MCP: Risk & Policy

WHAT IT DOES

What wait_for_url does on MacWright

AI agents invoke wait_for_url to trigger actions in MacWright. 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_url needs a policy

This tool monitors and potentially influences browser navigation state in Safari, which constitutes external operation execution. While it does not directly execute code or shell commands, it controls browser automation whose effects (page loading, navigation completion) depend on runtime state. The tool is part of a macOS automation suite ('native macOS desktop control') used for triggering external operations.

From the tool's definition Tool performs browser navigation control ('Wait until the current Safari page URL'), requiring Safari to be running and monitoring state. This is an external operation that triggers or verifies browser behavior based on dynamic conditions.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

wait_for_url Rate-limited

wait_for_url 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_url": {
      "limits": [
        {
          "counter": "wait_for_url_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 MacWright, so you can run agents against it safely.

FAQ

Questions about wait_for_url

What does the wait_for_url tool do? +

Wait until the current Safari page URL contains (or matches) a specified pattern. Useful after clicking links, submitting forms, or triggering navigation to verify the correct page loaded. Use regex:true for pattern matching (e.g. It is categorised as a Execute tool in the MacWright 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_url? +

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

What risk level is wait_for_url? +

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

Can I rate-limit wait_for_url? +

Yes. Add a rate_limit block to the wait_for_url 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_url completely? +

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

wait_for_url is provided by the MacWright MCP server (ruchit-p/macwright). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.