최상위 창 목록을 ClassName/ProcessId 와 함께 반환합니다.
AI agents call ui_list_windows to retrieve information from K-Personal MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a passive enumeration of open windows on the desktop. It gathers information about the UI state but does not modify, execute, delete, or control any windows—it merely lists them. This is a classic Read operation with minimal security risk, as it only exposes metadata about running applications that may already be visible or inferable by an agent with desktop access.
From the tool's definition Tool name 'ui_list_windows' and description indicate it 'returns a list of top-level windows' with metadata (ClassName/ProcessId). This is a query operation that retrieves window information without modifying state.
Attacks that exploit this kind of access
최상위 창 목록을 ClassName/ProcessId 와 함께 반환합니다. It is categorised as a Read tool in the K-Personal MCP MCP Server, which means it retrieves data without modifying state.
Register the K-Personal MCP server in PolicyLayer and add a rule for ui_list_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 K-Personal MCP. Nothing to install.
ui_list_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 ui_list_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 ui_list_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.
ui_list_windows is provided by the K-Personal MCP server (lee30934-byte/k-personal-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 →