Find a DOM element in Safari by CSS selector and return its screen coordinates for clicking. Automatically computes screen position from Safari window bounds + viewport offset. Returns center point (x, y) ready for use with click(). Includes aria-label when present. Form elements (input/textarea/...
AI agents call find_element to retrieve information from MacWright without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only reads/queries DOM element information and computes screen coordinates. It does not perform any clicks or modifications itself — it retrieves element properties (position, aria-label, form attributes) for use by other tools. No side effects are produced by this tool alone.
From the tool's definition Find a DOM element in Safari by CSS selector and return its screen coordinates for clicking... Returns center point (x, y) ready for use with click()
Attacks that exploit this kind of access
Find a DOM element in Safari by CSS selector and return its screen coordinates for clicking. Automatically computes screen position from Safari window bounds + viewport offset. Returns center point (x, y) ready for use with click(). Includes aria-label when present. Form elements (input/textarea/select) also include type, name, checked, value, disabled, and required. Use this instead of guessing coordinates for web automation. It is categorised as a Read tool in the MacWright MCP Server, which means it retrieves data without modifying state.
Register the MacWright MCP server in PolicyLayer and add a rule for find_element: 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.
find_element 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_element 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_element. 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_element 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 →