android_device · Android MCP: Risk & Policy

WHAT IT DOES

What android_device does on Android MCP

AI agents invoke android_device to trigger actions in Android 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 android_device needs a policy

The server provides full Android device control. With an empty description, the exact function is unknown, but given sibling tools covering screen, interaction, files, system, apps, and automation, 'android_device' likely manages device-level operations (pairing, settings, rebooting, etc.). This falls under Execute given the broader context, though confidence is low due to the empty description.

From the tool's definition Tool name 'android_device' on a server described as enabling 'full Android control' including 'app management' and 'system control'; tool description is empty.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

android_device Rate-limited

android_device 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": {
    "android_device": {
      "limits": [
        {
          "counter": "android_device_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 MCP, so you can run agents against it safely.

FAQ

Questions about android_device

What does the android_device tool do? +

android_device. It is categorised as a Execute tool in the Android 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 android_device? +

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

What risk level is android_device? +

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

Can I rate-limit android_device? +

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

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

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