avd_stop · AVD MCP Server MCP: Risk & Policy

WHAT IT DOES

What avd_stop does on AVD MCP Server

AI agents invoke avd_stop to trigger actions in AVD 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 avd_stop needs a policy

This tool executes an external command (adb emu kill) that triggers system-level operations on the host machine. While the action itself is not destructive (the emulator state can be restarted), it forcibly terminates a running process, which qualifies as Execute rather than Write.

From the tool's definition Tool performs 'adb emu kill' command to terminate a running Android Virtual Device emulator. The description states it 'Encerra um emulador online' (terminates an online emulator) via the kill command.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

avd_stop Rate-limited

avd_stop 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": {
    "avd_stop": {
      "limits": [
        {
          "counter": "avd_stop_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 AVD MCP Server, so you can run agents against it safely.

FAQ

Questions about avd_stop

What does the avd_stop tool do? +

Encerra um emulador online via adb emu kill (serial opcional). It is categorised as a Execute tool in the AVD 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 avd_stop? +

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

What risk level is avd_stop? +

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

Can I rate-limit avd_stop? +

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

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

avd_stop is provided by the AVD MCP Server MCP server (jramalho/avd-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.