AI agents call list_open_windows to retrieve information from MCP Windows without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves window information from the system without modifying, executing, or destroying anything. It is a passive read-only operation that returns metadata about currently open windows. The low severity reflects minimal blast radius—information disclosure about open windows is relatively benign compared to system-modifying operations.
From the tool's definition Tool name is 'list_open_windows' and description states 'Return a list of all top-level visible windows.' This is a query operation that retrieves information with no side effects.
Documented attack patterns abuse exactly the kind of access list_open_windows 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 list_open_windows:
{
"version": "1",
"default": "deny",
"tools": {
"list_open_windows": {}
}
}list_open_windows is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Return a list of all top-level visible windows. It is categorised as a Read tool in the MCP Windows MCP Server, which means it retrieves data without modifying state.
Register the MCP Windows MCP server in PolicyLayer and add a rule for list_open_windows: 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.
list_open_windows is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_open_windows 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 list_open_windows. 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.
list_open_windows 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.