AI agents call find_elements_in_app to retrieve information from Playwright MCP for macOS without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears designed to locate or enumerate UI elements within a macOS application without modifying state. While nominally read-only, the severity is elevated to 'medium' because discovered element positions/selectors can be weaponized by companion Execute tools (like 'click_element_by_selector' or 'type_text_to_element_by_selector') to automate sensitive actions.
From the tool's definition Tool name 'find_elements_in_app' and context as a sibling to 'click_element_by_selector' and 'get_element_details' suggest UI element discovery/querying. No description provided, but pattern matches read-only inspection tools on this Playwright MCP server.
Documented attack patterns abuse exactly the kind of access find_elements_in_app gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Playwright MCP for macOS, and nothing reaches the server without passing your rules. This is the rule we recommend for find_elements_in_app:
{
"version": "1",
"default": "deny",
"tools": {
"find_elements_in_app": {}
}
}find_elements_in_app is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
find_elements_in_app. It is categorised as a Read tool in the Playwright MCP for macOS MCP Server, which means it retrieves data without modifying state.
Register the Playwright MCP for macOS MCP server in PolicyLayer and add a rule for find_elements_in_app: 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 Playwright MCP for macOS. Nothing to install.
find_elements_in_app 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_elements_in_app 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_elements_in_app. 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_elements_in_app is provided by the Playwright MCP for macOS MCP server (mb-dev/macos-ui-automation-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Playwright MCP for macOS, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
9 Playwright MCP for macOS tools catalogued and risk-classified — across an index of 43,000+ MCP servers.