browser-use
Verified · 34 days agoControl a real Chrome browser to complete any task: fill forms, extract data, book flights.
Deterministic UI extraction and screenshot diffing for AI coding agents.
claude mcp add one-shot-ui -- npx -y [email protected]
A serious visual-regression and UI-copying toolkit exposed to agents through MCP: screenshot capture, style-token extraction, diffing, fix suggestions, and convergence loops. The repo has a real monorepo with tests across capture, diff, matching, optimizer, and MCP packages. It depends on Playwright and image/OCR tooling, so expect a heavier local install than a thin API wrapper.
Control a real Chrome browser to complete any task: fill forms, extract data, book flights.
Web scraping with stealth HTTP, real browsers, and Cloudflare bypass. CSS selectors supported.
MCP server for browser use access
Playwright Tools for MCP
AI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions.
AI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions.