window
AI agents invoke window to trigger actions in Windows Computer Use. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Given the server's purpose of fully controlling a Windows desktop with low-level input injection and the sibling tools (act, play, process, record, screenshot, system), a 'window' tool likely manages or interacts with windows (focus, resize, open, close). This constitutes an Execute-level action as it triggers external operations on the desktop environment. Confidence is lowered due to the empty description.
From the tool's definition Tool name 'window' on a server described as enabling 'full control of a Windows desktop with native screen capture, low-level input injection, game-grade input, and play-testing capabilities.' The tool description is empty.
Attacks that exploit this kind of access
window. It is categorised as a Execute tool in the Windows Computer Use MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Windows Computer Use MCP server in PolicyLayer and add a rule for 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 Windows Computer Use. Nothing to install.
window is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the 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 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.
window is provided by the Windows Computer Use MCP server (sshh12/windows-computer-use-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →