browser-use
Verified · 41 days agoBrowser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.
Give AI agents clean, LLM-ready web data — scrape any URL to markdown or extract structured JSON.
claude mcp add perpage-mcp-server -- npx -y @perpage/[email protected]
A clean two-tool wrapper — scrape a URL to LLM-ready markdown, or extract JSON against your own schema — around the PerPage scraping API, which you access by subscribing on RapidAPI. The npm code is small and does exactly what it says, but the backend is entirely closed-source and there is no repo anywhere despite the GitHub-flavored registry name; the publishing account's only public activity is old AI-project forks. Fine as a thin convenience shim if you already want PerPage; the crowded scrape-to-markdown space has more battle-tested options.
Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.
Web scraping with stealth HTTP, real browsers, and Cloudflare bypass. CSS selectors supported.
MCP server for browser use access
Playwright Tools for MCP
draw.io diagrams your AI agent draws on a live browser canvas that you can also edit by hand
AI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions.