AI agents invoke simctl_launch_app to trigger actions in Simctl. 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.
Launching an app on an iOS Simulator triggers execution of application code whose effects depend on which app is launched and its internal logic. This is an Execute operation rather than Read (it performs an action, not just retrieval), Write (it's not creating/modifying persistent data), or Destructive (it's reversible—the app can be terminated).
From the tool's definition Tool name 'simctl_launch_app' indicates launching an application; server description confirms this provides 'app...operations' and 'enabling device, app, media, and testing operations'.
Attacks that exploit this kind of access
simctl_launch_app. It is categorised as a Execute tool in the Simctl MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Simctl MCP server in PolicyLayer and add a rule for simctl_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 Simctl. Nothing to install.
simctl_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 simctl_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 simctl_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.
simctl_launch_app is provided by the Simctl MCP server (nzrsky/simctl-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →