获取程序的界面布局说明，提供操作的初始化向量。首次操作某程序时应调用此工具。
AI agents call screen_get_layout 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.
The tool retrieves and provides information about a program's UI layout to initialize operations. It reads/queries the current state of a desktop application without modifying, executing, or deleting anything. This is purely informational, fitting the Read category. Severity is low because examining UI layout poses minimal risk even if misused by an agent.
From the tool's definition Tool name 'screen_get_layout' and description stating it retrieves/provides interface layout information ('获取程序的界面布局说明，提供操作的初始化向量') as an initialization step before operating a program. This is a reconnaissance action with no side effects.
Attacks that exploit this kind of access
获取程序的界面布局说明，提供操作的初始化向量。首次操作某程序时应调用此工具。. 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_get_layout: 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_get_layout 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_get_layout 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_get_layout. 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_get_layout 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 →