AI agents call check_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 queries the state of UI elements on screen, which is a read-only operation with no side effects. It does not create, modify, delete, execute code, or trigger external operations. The server's purpose (GUI grounding for automation) confirms this is used for locating and inspecting UI elements rather than interacting with them destructively.
From the tool's definition Tool name 'check_element' and description 'Check the state of a UI element' indicate a query/inspection operation that retrieves the current state of a UI element without modifying it.
Attacks that exploit this kind of access
Check the state of a UI element. 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 check_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.
check_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 check_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 check_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.
check_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.
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 →