AI agents call find_element to retrieve information from Uitars without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves positional data about UI elements on screen. While it supports automation workflows, the tool itself performs no action—it only returns read-only information (pixel coordinates). The actual clicking or interaction would be performed by a separate Execute-category tool.
From the tool's definition Tool 'find_element' is described as locating UI elements and returning coordinates—a pure query operation with no side effects.
Attacks that exploit this kind of access
Find a UI element by description. Returns click coordinates in native screen pixels. It is categorised as a Read tool in the Uitars MCP Server, which means it retrieves data without modifying state.
Register the Uitars MCP server in PolicyLayer and add a rule for find_element: 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 Uitars. Nothing to install.
find_element 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 find_element 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 find_element. 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.
find_element is provided by the Uitars MCP server (lxsoftroxs/uitars-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
find_element is one line of Uitars's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →