Launch an installed app on a simulator
AI agents invoke launch_app to trigger actions in Simulator. 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.
This tool performs an action that executes code (the app launch) and produces observable side effects on the simulator environment. While not destructive by itself, launching arbitrary apps can trigger unintended consequences depending on what the app does (network calls, data access, modifications). This fits Execute rather than Write because it runs code rather than simply creating/modifying data.
From the tool's definition Tool launches an installed app on a simulator, which triggers external operations and execution of application code whose effects depend on which app is launched and its behavior.
Documented attack patterns abuse exactly the kind of access launch_app gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Simulator, and nothing reaches the server without passing your rules. This is the rule we recommend for launch_app:
{
"version": "1",
"default": "deny",
"tools": {
"launch_app": {
"limits": [
{
"counter": "launch_app_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}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.
Free to start. No card required.
Launch an installed app on a simulator. It is categorised as a Execute tool in the Simulator MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Simulator 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 Simulator. Nothing to install.
launch_app is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
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.
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.
launch_app is provided by the Simulator MCP server (joshuarileydev/simulator-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Simulator, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 Simulator tools catalogued and risk-classified — across an index of 43,000+ MCP servers.