AI agents call get_ui_elements to retrieve information from Mac without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs passive introspection of application UI structure. It queries and returns information about UI elements without creating, modifying, deleting, or executing any actions. Comparable to 'list' or 'get' operations in the Read category. The ability to inspect UI elements is prerequisite information for other tools on the server (like click_ui_element) but has no autonomous impact on system state.
From the tool's definition Tool name 'get_ui_elements' and description 'Retrieves the UI element tree for an application' clearly indicate data retrieval with no side effects. The maxDepth parameter is a read-limiting control, not a modification mechanism.
Attacks that exploit this kind of access
Retrieves the UI element tree for an application. Use maxDepth to limit tree depth. It is categorised as a Read tool in the Mac MCP Server, which means it retrieves data without modifying state.
Register the Mac MCP server in PolicyLayer and add a rule for get_ui_elements: 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 Mac. Nothing to install.
get_ui_elements 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 get_ui_elements 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 get_ui_elements. 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.
get_ui_elements is provided by the Mac MCP server (laststance/mac-mcp-server). 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 →