install_app · Espresso MCP: Risk & Policy

WHAT IT DOES

What install_app does on Espresso

AI agents invoke install_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 install_app needs a policy

Installing an APK on a device executes an external operation that installs potentially arbitrary code onto the device. This goes beyond a simple write (creating a file) because it involves the Android package manager processing and registering the application, which could introduce malware or unwanted software. It is an Execute-level action with high severity since a malicious APK could compromise device security.

From the tool's definition Install an App APK on the connected Android device

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

install_app Rate-limited

install_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": {
    "install_app": {
      "limits": [
        {
          "counter": "install_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 install_app

What does the install_app tool do? +

Install an App APK 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 install_app? +

Register the Espresso MCP server in PolicyLayer and add a rule for install_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 install_app? +

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

Can I rate-limit install_app? +

Yes. Add a rate_limit block to the install_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 install_app completely? +

Set action: deny in the PolicyLayer policy for install_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 install_app? +

install_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.