stop_app · Espresso MCP: Risk & Policy

WHAT IT DOES

What stop_app does on Espresso

AI agents invoke stop_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 stop_app needs a policy

This is an Execute action: it triggers an external operation (Android app termination) whose effects depend on which app is targeted. While not destructive in the data-deletion sense, stopping an app is an active intervention that disrupts running services and user sessions, making it Execute rather than Write.

From the tool's definition Tool performs 'stop an app on the connected Android device' — a runtime operation that terminates a process with immediate side effects.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

stop_app Rate-limited

stop_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": {
    "stop_app": {
      "limits": [
        {
          "counter": "stop_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 stop_app

What does the stop_app tool do? +

Stop 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 stop_app? +

Register the Espresso MCP server in PolicyLayer and add a rule for stop_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 stop_app? +

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

Can I rate-limit stop_app? +

Yes. Add a rate_limit block to the stop_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 stop_app completely? +

Set action: deny in the PolicyLayer policy for stop_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 stop_app? +

stop_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.