AI agents call screenshot_window 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.
Screenshot operations capture and return visual information without side effects. While screenshots can reveal sensitive information on screen, the tool itself performs only read/retrieval of existing display data. The empty description lowers confidence slightly, but the sibling tool pattern and name clearly indicate a non-destructive, non-modifying operation.
From the tool's definition Tool named 'screenshot_window' with no description. Based on sibling tools (get_clipboard, get_foreground_window_info, get_media_sessions, get_theme_mode, get_volume, get_window_list, list_open_windows) that are all retrieval operations, and the pattern of…
Documented attack patterns abuse exactly the kind of access screenshot_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 screenshot_window:
{
"version": "1",
"default": "deny",
"tools": {
"screenshot_window": {}
}
}screenshot_window 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.
screenshot_window. 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 screenshot_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.
screenshot_window 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 screenshot_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 screenshot_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.
screenshot_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.