AI agents invoke click_menu_item to trigger actions in MacWright. 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.
This tool triggers UI actions by clicking menu bar items, which can execute arbitrary application commands (e.g., Save, Delete, Quit, Format disk) depending on the menu path provided. The effects are highly variable and potentially irreversible depending on which menu item is clicked, making it an Execute-category tool with high severity due to the wide blast radius of possible menu-triggered operations.
From the tool's definition Click a native macOS menu bar item by path
Attacks that exploit this kind of access
Click a native macOS menu bar item by path, or list available menu items. It is categorised as a Execute tool in the MacWright MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MacWright 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 MacWright. 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 MacWright MCP server (ruchit-p/macwright). 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 →