Click a visible element in Safari by its text content or aria-label. Finds the most specific element (shortest text) containing the specified text and clicks it. On equal length, prefers interactive elements (a, button, input). Useful when you don
AI agents invoke click_text 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 performs a browser click action in Safari, triggering external operations whose effects depend on what is clicked. Clicking elements can submit forms, navigate pages, trigger purchases, delete data, or initiate any arbitrary web action — making it an Execute-category tool with high blast radius since an AI agent could click any interactive element on screen.
From the tool's definition Click a visible element in Safari by its text content or aria-label... clicks it
Attacks that exploit this kind of access
Click a visible element in Safari by its text content or aria-label. Finds the most specific element (shortest text) containing the specified text and clicks it. On equal length, prefers interactive elements (a, button, input). Useful when you don. 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_text: 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_text 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_text 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_text. 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_text 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 →