컨트롤을 이름·역할·AutomationId 로 검색해 매칭 노드 경로를 반환합니다.
AI agents call ui_find 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 UI element discovery and inspection only. It retrieves information about desktop UI structure and locates controls by their properties, which is a read-only operation. While it enables subsequent UI automation, the tool itself does not execute commands, modify state, or perform destructive actions.
From the tool's definition Tool searches for UI controls by name, role, or AutomationId and returns matching node paths. The description indicates a query/search operation ('검색해 매칭 노드 경로를 반환' = 'search and return matching node paths') with no modification, deletion, or execution of…
Attacks that exploit this kind of access
컨트롤을 이름·역할·AutomationId 로 검색해 매칭 노드 경로를 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_find: 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_find 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_find 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_find. 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_find 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 →