hover_and_wait · MacWright MCP: Risk & Policy

WHAT IT DOES

What hover_and_wait does on MacWright

AI agents invoke hover_and_wait 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 hover_and_wait needs a policy

This tool executes a sequence of GUI automation actions: mouse movement (Move), state monitoring (wait for tooltip), and screenshot capture (take screenshot). While not destructive or financial, it performs active operations that control the macOS desktop and interact with application state, which falls under Execute rather than Read.

From the tool's definition Tool performs mouse movement to coordinates or AX elements, waits for UI state change (tooltip/popover appearance), and triggers screenshot capture.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

hover_and_wait Rate-limited

hover_and_wait 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": {
    "hover_and_wait": {
      "limits": [
        {
          "counter": "hover_and_wait_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 hover_and_wait

What does the hover_and_wait tool do? +

Move mouse to coordinates (or to an AX element by text label), wait for tooltip/popover to appear, then take a screenshot. 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 hover_and_wait? +

Register the MacWright MCP server in PolicyLayer and add a rule for hover_and_wait: 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 hover_and_wait? +

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

Can I rate-limit hover_and_wait? +

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

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

hover_and_wait 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.