launch_app · Phantom MCP: Risk & Policy

WHAT IT DOES

What launch_app does on Phantom

AI agents invoke launch_app to trigger actions in Phantom. 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 launch_app needs a policy

This tool executes code/operations on real or simulated devices by launching applications. While launching a benign app is low-risk, the blast radius is high because: (1) an AI agent could be tricked into launching malicious or unwanted applications, (2) launching apps with side effects (payment apps, data deletion utilities, etc.) could cause unintended consequences, (3) repeated launches could DoS the device.

From the tool's definition Tool name 'launch_app' combined with description 'Lance une app sur le device actif' (Launch an app on the active device) indicates execution of an external operation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

launch_app Rate-limited

launch_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": {
    "launch_app": {
      "limits": [
        {
          "counter": "launch_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 Phantom, so you can run agents against it safely.

FAQ

Questions about launch_app

What does the launch_app tool do? +

Lance une app sur le device actif. iOS : bundle ID (ex: com.monapp.ios). Android : package name (ex: com.monapp.android). It is categorised as a Execute tool in the Phantom MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on launch_app? +

Register the Phantom MCP server in PolicyLayer and add a rule for launch_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 Phantom. Nothing to install.

What risk level is launch_app? +

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

Can I rate-limit launch_app? +

Yes. Add a rate_limit block to the launch_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 launch_app completely? +

Set action: deny in the PolicyLayer policy for launch_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 launch_app? +

launch_app is provided by the Phantom MCP server (nthimpulse/phantom-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.