start_app · Espresso MCP: Risk & Policy

WHAT IT DOES

What start_app does on Espresso

AI agents invoke start_app to trigger actions in Espresso. 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 start_app needs a policy

This tool triggers execution of arbitrary applications on an Android device, which constitutes an Execute risk. The effects depend on which app is started and could range from harmless (launching a calculator) to severe (starting apps that access sensitive data, make calls, send messages, or perform financial transactions).

From the tool's definition Tool name 'start_app' with description 'Start an app on the connected Android device' indicates execution of external operations (launching applications) on a mobile device.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_app Rate-limited

start_app 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": {
    "start_app": {
      "limits": [
        {
          "counter": "start_app_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 Espresso, so you can run agents against it safely.

FAQ

Questions about start_app

What does the start_app tool do? +

Start an app on the connected Android device. It is categorised as a Execute tool in the Espresso MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on start_app? +

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

What risk level is start_app? +

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

Can I rate-limit start_app? +

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

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

start_app is provided by the Espresso MCP server (vs4vijay/espresso-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.