AI agents call close_window to permanently remove resources in PyMCPAutoGUI — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Closing a window cannot be undone programmatically; any unsaved state in the target application is lost. An AI agent misusing this tool could close critical applications or cause data loss, warranting a high severity Destructive classification.
From the tool's definition 'Closes the first window matching the title' — closing a window is an irreversible action that terminates the application and may discard unsaved work.
Documented attack patterns abuse exactly the kind of access close_window gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and PyMCPAutoGUI, and nothing reaches the server without passing your rules. This is the rule we recommend for close_window:
{
"version": "1",
"default": "deny",
"hide": [
"close_window"
]
}close_window 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.
Closes the first window matching the title. It is categorised as a Destructive tool in the PyMCPAutoGUI MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the PyMCPAutoGUI MCP server in PolicyLayer and add a rule for close_window: 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 PyMCPAutoGUI. Nothing to install.
close_window 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 close_window 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 close_window. 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.
close_window is provided by the PyMCPAutoGUI MCP server (kitfactory/pymcpautogui). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from PyMCPAutoGUI, 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.
34 PyMCPAutoGUI tools catalogued and risk-classified — across an index of 43,000+ MCP servers.