browser-use
Verified · 33 days agoControl a real Chrome browser to complete any task: fill forms, extract data, book flights.
LionScraper Node: MCP stdio + CLI + HTTP API bridging AI to LionScraper browser extension.
claude mcp add lionscraper-node -- npx -y [email protected]
An honest thin bridge, and it says so itself: 'the real scraping logic runs in the extension.' This npm package gives you MCP stdio, a CLI, and a loopback HTTP API that all forward to the proprietary LionScraper Chrome/Edge extension (live on both stores), which does the actual page scraping; without the extension you get a degraded plain-HTTP fetch fallback with no JS execution. Well-documented for what it is, but you're adopting a closed-source extension from a one-repo, zero-follower publisher — the auditable part is only the plumbing.
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.