ui_get_element
AI agents call ui_get_element to retrieve information from UI Bridge MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite empty description, the name 'get_element' and positioning among inspection tools (diagnose, analyze, search, screenshot) indicate this retrieves UI element data for inspection. No modification or execution is implied. Severity is medium rather than low because UI inspection could reveal sensitive UI state or data if an agent queries unintended screens, though this is dependent on what data the tool exposes.
From the tool's definition Tool name 'ui_get_element' combined with server context: retrieves or inspects UI element information without modifying state. Sibling tools like 'sdk_ai_search' and 'sdk_annotated_screenshot' confirm the server's inspection-focused design.
Attacks that exploit this kind of access
ui_get_element. It is categorised as a Read tool in the UI Bridge MCP MCP Server, which means it retrieves data without modifying state.
Register the UI Bridge MCP server in PolicyLayer and add a rule for ui_get_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 UI Bridge MCP. Nothing to install.
ui_get_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 ui_get_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 ui_get_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.
ui_get_element is provided by the UI Bridge MCP server (qontinui/ui-bridge-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 →