Resize a specific application window (e.g.,
AI agents invoke Resize-Tool to trigger actions in Windows-MCP. 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.
Resizing an application window is an external system operation that affects the state of the OS UI. It is not a simple read and has side effects on the running environment, placing it in Execute. Severity is medium because misuse could disrupt workflows but is generally reversible and limited in blast radius. Confidence is slightly reduced because the description is truncated and incomplete.
From the tool's definition Resize a specific application window — triggers an external operation on the Windows UI/window manager
Attacks that exploit this kind of access
Resize a specific application window (e.g.,. It is categorised as a Execute tool in the Windows-MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Windows- MCP server in PolicyLayer and add a rule for Resize-Tool: 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-MCP. Nothing to install.
Resize-Tool 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 Resize-Tool 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 Resize-Tool. 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.
Resize-Tool is provided by the Windows- MCP server (zhouke2020/cursortouch-windows-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 →