adb_input_text · LocalAnt MCP: Risk & Policy

WHAT IT DOES

What adb_input_text does on LocalAnt

AI agents invoke adb_input_text to trigger actions in LocalAnt. 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 adb_input_text needs a policy

This tool sends keystrokes/text input to a physical or emulated Android device. It executes an external operation (ADB input) whose effects depend on arguments — text could be typed into any active field including passwords, commands, or forms. The server description confirms this is part of a suite for PC/device control via shell and automation tools.

From the tool's definition 'Type text on the device' — triggers external input operation on a connected Android device via ADB

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

adb_input_text Rate-limited

adb_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": {
    "adb_input_text": {
      "limits": [
        {
          "counter": "adb_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 LocalAnt, so you can run agents against it safely.

FAQ

Questions about adb_input_text

What does the adb_input_text tool do? +

Type text on the device (audited). It is categorised as a Execute tool in the LocalAnt MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on adb_input_text? +

Register the LocalAnt MCP server in PolicyLayer and add a rule for adb_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 LocalAnt. Nothing to install.

What risk level is adb_input_text? +

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

Can I rate-limit adb_input_text? +

Yes. Add a rate_limit block to the adb_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 adb_input_text completely? +

Set action: deny in the PolicyLayer policy for adb_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 adb_input_text? +

adb_input_text is provided by the LocalAnt MCP server (yuga-hashimoto/localant). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.