tap_screen · MCP Connect MCP: Risk & Policy

WHAT IT DOES

What tap_screen does on MCP Connect

AI agents invoke tap_screen to trigger actions in MCP Connect. 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_screen needs a policy

This tool triggers a gesture/interaction on an iOS Simulator screen, which constitutes executing an external operation (a UI action). The effect depends on what is at the tapped coordinates — it could trigger arbitrary app behavior, navigation, or data changes, making it Execute-level. Misuse could cause unintended actions within the simulated app.

From the tool's definition Taps the simulator screen at the specified coordinates (x, y)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

tap_screen Rate-limited

tap_screen 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_screen": {
      "limits": [
        {
          "counter": "tap_screen_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 MCP Connect, so you can run agents against it safely.

FAQ

Questions about tap_screen

What does the tap_screen tool do? +

Taps the simulator screen at the specified coordinates (x, y). It is categorised as a Execute tool in the MCP Connect 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_screen? +

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

What risk level is tap_screen? +

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

Can I rate-limit tap_screen? +

Yes. Add a rate_limit block to the tap_screen 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_screen completely? +

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

tap_screen is provided by the MCP Connect MCP server (plaintest/mcp-connect). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.