app_launch · AVD MCP Server MCP: Risk & Policy

WHAT IT DOES

What app_launch does on AVD MCP Server

AI agents invoke app_launch 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 app_launch needs a policy

Launching applications via monkey (a fuzzing/execution tool) or am start (Android Activity Manager) triggers code execution on the Android Virtual Device. While not destructive per se, the effects depend entirely on what the target application does when launched, making this an Execute category risk. In a compromised or adversarial scenario, an AI agent could launch malicious apps or apps with side effects.

From the tool's definition Tool description states it launches apps 'por monkey ou am start' (via monkey or am start), which are Android methods for executing application code.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

app_launch Rate-limited

app_launch 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": {
    "app_launch": {
      "limits": [
        {
          "counter": "app_launch_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 app_launch

What does the app_launch tool do? +

Abre o app por monkey ou am start quando activity for informada. 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 app_launch? +

Register the AVD MCP Server MCP server in PolicyLayer and add a rule for app_launch: 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 app_launch? +

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

Can I rate-limit app_launch? +

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

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

app_launch 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.