AI agents call close_window to permanently remove resources in MCP Windows — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Closing a window can cause irreversible loss of unsaved data in the affected application. While not a data deletion operation per se, it is an irreversible action that cannot be undone. The description is empty, lowering confidence, but the name strongly implies termination of a window/process. Ranked Destructive over Execute due to the irreversible nature of potential data loss.
From the tool's definition Tool name is 'close_window'; description is empty. Based on name alone, closing a window terminates an application or window session, which may be irreversible (unsaved work lost).
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 MCP Windows, 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.
close_window. It is categorised as a Destructive tool in the MCP Windows MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Windows 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 MCP Windows. 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 MCP Windows MCP server (secretiveshell/mcp-windows). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Windows, 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.
28 MCP Windows tools catalogued and risk-classified — across an index of 43,000+ MCP servers.