Shut down a running simulator/emulator.
AI agents use shutdown_device to create or update resources in React Native Dev — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your React Native Dev environment.
An AI agent can call shutdown_device faster than any human can review — one bad instruction and it creates or modifies resources in React Native Dev by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Shut down a running simulator/emulator. It is categorised as a Write tool in the React Native Dev MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the React Native Dev MCP server in PolicyLayer and add a rule for shutdown_device: 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 React Native Dev. Nothing to install.
shutdown_device is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the shutdown_device 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_device. 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_device is provided by the React Native Dev MCP server (luizhbesper/react-native-mcp). 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 →