Terminate app by bundle ID or package name. No app connection required.
AI agents call terminate_app to permanently remove resources in React Native — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Terminating an application is an irreversible action at the moment it occurs — the running process is forcefully killed, any unsaved state is lost, and active connections are dropped. While the app can be relaunched, the act of termination itself cannot be undone, making this Destructive. The blast radius is high because misuse could kill production or critical apps, causing service disruption and data loss.
From the tool's definition Terminate app by bundle ID or package name
Attacks that exploit this kind of access
Terminate app by bundle ID or package name. No app connection required. It is categorised as a Destructive tool in the React Native MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the React Native MCP server in PolicyLayer and add a rule for terminate_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 React Native. Nothing to install.
terminate_app 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 terminate_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 terminate_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.
terminate_app is provided by the React Native MCP server (@ohah/react-native-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 →