press_button · App Screen MCP: Risk & Policy

WHAT IT DOES

What press_button does on App Screen

AI agents invoke press_button to trigger actions in App Screen. 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 press_button needs a policy

This tool triggers an action on an iOS Simulator by simulating hardware button presses (e.g., Home, Power, Volume). It executes an external operation on a device, which can cause state changes (locking the device, returning to home screen, etc.) that may affect the agent's automation workflow. It doesn't read data, but it does execute device-level interactions with real side effects.

From the tool's definition Press a hardware button on the simulator

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

press_button Rate-limited

press_button 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": {
    "press_button": {
      "limits": [
        {
          "counter": "press_button_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 App Screen, so you can run agents against it safely.

FAQ

Questions about press_button

What does the press_button tool do? +

Press a hardware button on the simulator. It is categorised as a Execute tool in the App Screen MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on press_button? +

Register the App Screen MCP server in PolicyLayer and add a rule for press_button: 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 App Screen. Nothing to install.

What risk level is press_button? +

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

Can I rate-limit press_button? +

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

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

press_button is provided by the App Screen MCP server (xmuweili/app-screen-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.