android_input_text · Android MCP Server MCP: Risk & Policy

WHAT IT DOES

What android_input_text does on Android MCP Server

AI agents invoke android_input_text to trigger actions in Android MCP Server. 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_input_text needs a policy

This tool executes an ADB command to inject text input into an Android device. It triggers an external operation on a real device, potentially entering credentials, messages, commands, or other sensitive data into any focused field. The effects depend on what text is injected and where — misuse could lead to unintended data entry, credential submission, or triggering actions on the device.

From the tool's definition 'Input text into the currently focused field on the Android device via ADB'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

android_input_text Rate-limited

android_input_text 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_input_text": {
      "limits": [
        {
          "counter": "android_input_text_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 Server, so you can run agents against it safely.

FAQ

Questions about android_input_text

What does the android_input_text tool do? +

Input text into the currently focused field on the Android device via ADB. It is categorised as a Execute tool in the Android MCP Server 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_input_text? +

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

What risk level is android_input_text? +

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

Can I rate-limit android_input_text? +

Yes. Add a rate_limit block to the android_input_text 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_input_text completely? +

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

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