Browser extension for annotating UI elements for AI agents
Browser extension for annotating UI elements for AI agents
Lightweight browser extension (Chrome + Edge + Firefox) + local MCP bridge for annotation-first UI pair programming.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"mcpServers": {
"onui-local": {
"command": "node",
"args": [
"/ABSOLUTE/PATH/TO/onUI/packages/mcp-server/dist/bin/onui-cli.js",
"mcp"
]
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
Use Microsoft’s Playwright MCP server to navigate pages, inspect accessibility snapshots, fill forms and capture browser screenshots.
The original Chromium automation reference server — simple, screenshot-driven browser control.
AI browser tools with Chrome CDP. Navigate, screenshot, interact. Multi-provider failover.
Connect your agent to any HTTP API on the fly — discover, map, and fetch typed data.
A Model Context Protocol (MCP) server for Selenium WebDriver — browser automation for AI agents.
screenshot-mcp binary for linux x64