AI agents call shutdown_simulator to permanently remove resources in Simulator — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Shutting down a simulator is not easily undone without re-booting and re-launching; any runtime state, in-memory data, or active sessions are lost. While the simulator itself is not deleted, the operational state is irreversibly destroyed, placing this in the Destructive category. Severity is medium because it affects only a virtual device environment, not production data.
From the tool's definition 'Shutdown an iOS simulator' — forcibly terminates a running simulator instance, which is an irreversible state change (the simulator stops and any unsaved/in-memory state is lost).
Documented attack patterns abuse exactly the kind of access shutdown_simulator 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 shutdown_simulator:
{
"version": "1",
"default": "deny",
"hide": [
"shutdown_simulator"
]
}shutdown_simulator disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Shutdown an iOS simulator. It is categorised as a Destructive tool in the Simulator MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Simulator MCP server in PolicyLayer and add a rule for shutdown_simulator: 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.
shutdown_simulator is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the shutdown_simulator 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 shutdown_simulator. 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.
shutdown_simulator 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.