AI agents invoke click 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.
Simulating mouse clicks at arbitrary coordinates is an Execute action — it triggers UI interactions whose effects depend entirely on what is at those coordinates (could open files, submit forms, delete items, etc.). The blast radius is high because an AI agent could click anything on screen, including destructive UI actions, without knowing in advance what will be triggered.
From the tool's definition Performs a mouse click at specified coordinates. Supports left, right, middle buttons and modifier keys
Attacks that exploit this kind of access
Performs a mouse click at specified coordinates. Supports left, right, middle buttons and modifier keys. 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: 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 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 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. 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 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 →