tap_relative · App Screen MCP: Risk & Policy

WHAT IT DOES

What tap_relative does on App Screen

AI agents invoke tap_relative 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 tap_relative needs a policy

Tapping is a browser/UI action that triggers external operations (button presses, navigation, form submissions) whose effects depend on where the tap lands. This falls under Execute as it drives simulator interactions that can have wide-ranging downstream effects depending on arguments.

From the tool's definition 'Tap using relative coordinates (rx, ry) in [0,1]' — performs a UI tap action on an iOS Simulator, triggering interactive UI events

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

tap_relative Rate-limited

tap_relative 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": {
    "tap_relative": {
      "limits": [
        {
          "counter": "tap_relative_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 tap_relative

What does the tap_relative tool do? +

Tap using relative coordinates (rx, ry) in [0,1] where (0.5, 0.5) is center. 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 tap_relative? +

Register the App Screen MCP server in PolicyLayer and add a rule for tap_relative: 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 tap_relative? +

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

Can I rate-limit tap_relative? +

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

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

tap_relative 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.