close_app

THE RISK

Critical Risk

Why close_app needs a policy

Closing an application is an irreversible action in the context of the running session — it terminates the process and any unsaved state is lost. This cannot be undone, making it Destructive. Severity is medium since it affects only the currently running test application rather than persistent data or system-wide resources.

From the tool's definition Close the currently running application

Documented attack patterns abuse exactly the kind of access close_app gives an agent:

POLICY

How to control close_app

PolicyLayer is an MCP gateway — it sits between your AI agents and Qt Pilot, and nothing reaches the server without passing your rules. This is the rule we recommend for close_app:

policy.json

{
  "version": "1",
  "default": "deny",
  "hide": [
    "close_app"
  ]
}

close_app disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

Create a free account and register Qt Pilot — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RESTRICT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Qt Pilot tools

Execute launch_app launch_app Execute trigger_action Trigger a QAction by its object name. Execute wait_for_idle Wait for the Qt application to process pending events. Execute hover_widget Hover over a widget by its object name. Execute click_at click_at Execute click_widget Click a widget by its object name. Execute press_key Simulate a key press. Execute type_text Type text into a widget or the currently focused widget.

All 15 Qt Pilot tools →

Destructive tools on other servers

Android Forensics ADB MCP Server create_full_backup 0xarchive web3_revoke_key Frida Game Hacking MCP clear_scan cPanel MCP Server clear_spam_box

Go deeper

Critical-risk tools in Qt Pilot → Every critical-risk tool this server exposes, in one view.
All critical-risk MCP tools → Every critical-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Blast radius → How much damage one compromised or confused agent can do — and how to bound it.
Tool call approval → Approval gates on individual tool calls: auto-allow, prompt, or deny.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about close_app

What does the close_app tool do? +

Close the currently running application. It is categorised as a Destructive tool in the Qt Pilot MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on close_app? +

Register the Qt Pilot MCP server in PolicyLayer and add a rule for close_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 Qt Pilot. Nothing to install.

What risk level is close_app? +

close_app is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit close_app? +

Yes. Add a rate_limit block to the close_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.

How do I block close_app completely? +

Set action: deny in the PolicyLayer policy for close_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.

What MCP server provides close_app? +

close_app is provided by the Qt Pilot MCP server (neatobandit0/qt-pilot). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Qt Pilot tool call.

Start from Qt Pilot, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →