ai_action · Android Tester MCP: Risk & Policy

WHAT IT DOES

What ai_action does on Android Tester MCP

AI agents invoke ai_action to trigger actions in Android Tester MCP. 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 ai_action needs a policy

This tool executes arbitrary UI actions on an Android device driven by natural language instructions. The effects depend entirely on what is instructed — it could tap buttons, enter text, submit forms, install apps, delete data, or trigger any in-app behavior.

From the tool's definition "Perform an action on the UI of the android box (natural language instruction)"

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ai_action Rate-limited

ai_action 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": {
    "ai_action": {
      "limits": [
        {
          "counter": "ai_action_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 Android Tester MCP, so you can run agents against it safely.

FAQ

Questions about ai_action

What does the ai_action tool do? +

Perform an action on the UI of the android box (natural language instruction). It is categorised as a Execute tool in the Android Tester MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on ai_action? +

Register the Android Tester MCP server in PolicyLayer and add a rule for ai_action: 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 Android Tester MCP. Nothing to install.

What risk level is ai_action? +

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

Can I rate-limit ai_action? +

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

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

ai_action is provided by the Android Tester MCP server (zhenweiwang1990/android-tester-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.