ai_web_elements
Scan a web page to extract every button, link, input, select, and clickable element with screen coordinates for automated mouse control.
Instructions
[AI-Optimized] Scan ALL interactive elements on a web page via Chrome DevTools Protocol. Auto-launches a CDP-enabled Chrome if needed. Provide a URL to navigate to, or omit to scan the current page. Detects every button, link, input, select, textarea, and clickable element with screen coordinates for mouse_click.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "ai_web_elements"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | No | URL to navigate to and scan. Omit to scan current page. | |
| cdpPort | No | Chrome DevTools Protocol port (default: 9222) | |
| tabIndex | No | Tab index to scan (default: 0 = first page tab) | |
| includeText | No | Include visible static text elements like headings and paragraphs (default: false) | |
| visibleOnly | No | Only return elements visible in viewport (default: true) |