当无法自动找到目标时，请求用户帮助定位元素。
AI agents call screen_ask_user_locate 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 requests user assistance to locate a UI element when automatic detection fails. It is primarily a read/query operation — it asks the user to identify a location on screen and returns that positional information. It does not click, type, or execute any action itself. The severity is low as it only queries for location data and requires human involvement, limiting autonomous misuse potential.
From the tool's definition Tool name 'screen_ask_user_locate' and description '当无法自动找到目标时，请求用户帮助定位元素' (When unable to automatically find the target, ask the user to help locate the element)
Attacks that exploit this kind of access
当无法自动找到目标时，请求用户帮助定位元素。. 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_ask_user_locate: 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_ask_user_locate 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_ask_user_locate 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_ask_user_locate. 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_ask_user_locate 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 →