launch_app_sim · Sl Test MCP: Risk & Policy

WHAT IT DOES

What launch_app_sim does on Sl Test

AI agents invoke launch_app_sim to trigger actions in Sl Test. 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_sim needs a policy

This tool executes arbitrary application code within a simulator environment based on caller-controlled parameters (simulatorUuid, bundleId). While contained within a simulator sandbox, successful misuse could lead to unintended application behavior, data exposure within the simulator, or resource exhaustion.

From the tool's definition Tool launches an app in an iOS simulator by executing the specified bundleId on a given simulatorUuid. The description explicitly instructs to 'Launches an app' which triggers external execution of mobile application code whose effects depend on which app is…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

launch_app_sim Rate-limited

launch_app_sim 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_sim": {
      "limits": [
        {
          "counter": "launch_app_sim_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 Sl Test, so you can run agents against it safely.

FAQ

Questions about launch_app_sim

What does the launch_app_sim tool do? +

Launches an app in an iOS simulator. IMPORTANT: You MUST provide both the simulatorUuid and bundleId parameters.\n\nNote: You must install the app in the simulator before launching. The typical workflow is: build → install → launch. Example: launch_app_sim({ simulatorUuid:. It is categorised as a Execute tool in the Sl Test 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_sim? +

Register the Sl Test MCP server in PolicyLayer and add a rule for launch_app_sim: 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 Sl Test. Nothing to install.

What risk level is launch_app_sim? +

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

Can I rate-limit launch_app_sim? +

Yes. Add a rate_limit block to the launch_app_sim 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_sim completely? +

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

launch_app_sim is provided by the Sl Test MCP server (sampsonky/xcodebuildmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.