Capture comprehensive desktop state including default language used by user interface, focused/opened applications, interactive UI elements (buttons, text fields, menus), informative content (text, labels, status), and scrollable areas. Optionally includes visual screenshot when use_vision=True. ...
AI agents call State-Tool to retrieve information from Windows-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and captures the current state of the desktop environment — enumerating open applications, UI elements, text content, and optionally screenshots. It has no side effects and does not modify, execute, or delete anything.
From the tool's definition Capture comprehensive desktop state including focused/opened applications, interactive UI elements, informative content, and scrollable areas
Attacks that exploit this kind of access
Capture comprehensive desktop state including default language used by user interface, focused/opened applications, interactive UI elements (buttons, text fields, menus), informative content (text, labels, status), and scrollable areas. Optionally includes visual screenshot when use_vision=True. Essential for understanding current desktop context and available UI interactions. It is categorised as a Read tool in the Windows-MCP MCP Server, which means it retrieves data without modifying state.
Register the Windows- MCP server in PolicyLayer and add a rule for State-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.
State-Tool 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 State-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 State-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.
State-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 →