列出所有已有的程序布局说明文件。
AI agents call screen_list_layouts 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 queries and returns information about previously learned UI layouts stored locally. It performs a read-only operation on layout metadata—no side effects, no data modification, no code execution, and no destructive actions. The low severity reflects that exposing a list of UI layout filenames presents minimal security risk, as it merely enumerates cached UI recognition patterns.
From the tool's definition Tool name 'screen_list_layouts' and description '列出所有已有的程序布局说明文件' (list all existing program layout instruction files) indicate retrieval of cached/stored layout metadata without modification or execution of external commands.
Attacks that exploit this kind of access
列出所有已有的程序布局说明文件。. 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_list_layouts: 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_list_layouts 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_list_layouts 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_list_layouts. 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_list_layouts 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 →