AI agents invoke click_menu_item to trigger actions in Mac. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Clicking a menu item triggers application actions that can have wide-ranging effects depending on which menu item is selected — from opening files to deleting data, quitting apps, or executing arbitrary application commands. The effect depends entirely on arguments (the menu path), making this an Execute-category tool. Severity is high because an AI agent could trigger destructive or sensitive application actions (e.
From the tool's definition Clicks a menu item by path
Attacks that exploit this kind of access
Clicks a menu item by path (e.g.,. It is categorised as a Execute tool in the Mac MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mac MCP server in PolicyLayer and add a rule for click_menu_item: 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.
click_menu_item is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the click_menu_item 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 click_menu_item. 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.
click_menu_item 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 →