扫描当前窗口所有 UI 元素（文字、图标、按钮等），生成带像素特征的 JSON 文件。整合 OCR、UIA、边缘检测多种识别方法，并对每个元素进行多点采样生成颜色特征。输出文件保存在 app_layouts/{app_name}/{app_name}_icon_features.json。
AI agents call screen_scan_ui_elements to retrieve information from Screen Agent 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 recognition and feature extraction through observation and analysis (OCR, edge detection, color sampling). It reads/scans the current window state and generates informational output (JSON with features) without modifying data, executing arbitrary code, or triggering side effects.
From the tool's definition The tool 'scans all UI elements in the current window (text, icons, buttons, etc.) and generates a JSON file with pixel features' using 'OCR, UIA, edge detection' and 'multi-point color sampling'.
Attacks that exploit this kind of access
扫描当前窗口所有 UI 元素（文字、图标、按钮等），生成带像素特征的 JSON 文件。整合 OCR、UIA、边缘检测多种识别方法，并对每个元素进行多点采样生成颜色特征。输出文件保存在 app_layouts/{app_name}/{app_name}_icon_features.json。. It is categorised as a Read tool in the Screen Agent MCP Server, which means it retrieves data without modifying state.
Register the Screen Agent MCP server in PolicyLayer and add a rule for screen_scan_ui_elements: 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 Screen Agent. Nothing to install.
screen_scan_ui_elements 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 screen_scan_ui_elements 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 screen_scan_ui_elements. 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.
screen_scan_ui_elements is provided by the Screen Agent MCP server (lqszhsp/screen-agent). 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 →