browser-use
Verified · 34 days agoControl a real Chrome browser to complete any task: fill forms, extract data, book flights.
Generate PDFs, screenshots, and documents via any MCP-compatible AI agent.
claude mcp add docapi -- npx -y @docapi/[email protected]
Thin but real client for DocAPI's hosted HTML-to-PDF/screenshot service — Chromium rendering, so modern CSS actually works, with images returned inline. Know what you're connecting to: it ships a docapi_register_agent tool that signs up an account mid-conversation (API key + USDC top-up address, 'no human step required') and nudges agents toward autonomous crypto payments on Base — fine if that's what you want, worth a pause if not. Three-month-old vendor, downloads still at mirror baseline, and the GitHub repo's README is bizarrely a copy of the MCP Registry's own README (the source and npm package are the real thing).
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.