What is webrain?
webrain is an open-source (MIT) Rust MCP server for LLM-driven browser automation and web scraping. It is one static binary that drives three browser engines (Chrome, Lightpanda, Obscura) plus a fast no-browser HTTP path, and it exposes 17 intent-based tools over the Model Context Protocol. Install it on any system, point any MCP client (GitHub Copilot, Claude, Codex, Cursor, …) at it, and the model decides everything — search, crawl, scrape, navigate, interact — from a plain-language prompt. No hardcoded intent detection, no daemon, no Node.js.Why webrain?
Web automation shouldn’t mean wiring up a driver, a browser download, and your own tool wrappers before an LLM can touch a page. Webrain collapses that into one binary + one install command and speaks MCP, so any LLM client drives it directly.Quickstart
Get a browser engine, start the MCP server, and drive it from a prompt in minutes.
What you can do with it
- Scrape at scale —
webrain_batchpagination +webrain_crawl(spider) with auto-throttle and checkpoint/resume;webrain_crawl(sitemap / scan) to map a site first. - Structured data without hand-written selectors —
webrain_extract(autoschema) probes the DOM, then schema / regex / table modes read container-level structure. - Stealth login — real-Chrome profiles with an encrypted local credential vault (AES-256-GCM + optional TOTP); transfer cookies across engines.
- Get past challenges — reads the
challengefield on every navigate and clears Cloudflare/Turnstile via real Chrome + a persistent profile and native login. - See the page —
webrain_observe(a11y / semantic / state), plus vision tiles (screenshot → vector store) for tables and charts. - Read anything —
webrain_pdf(extract + render), JSON-LD, media, pluswebrain_scrapefor static pages 10–100× faster than a browser.
How it’s built
Everything speaks Chrome DevTools Protocol over a raw WebSocket, so one
backend drives Chrome, Lightpanda, and Obscura interchangeably.
Prerequisites
- OS: Windows, macOS, or Linux (x86_64 / arm64).
- A browser engine — run
webrain installonce (downloads Chrome for Testing). Obscura and Lightpanda are optional extra engines. - Linux: system libraries for Chrome — see Installation.
- Docker — only to run the obscura / lightpanda engines in containers.
- An MCP-capable client (VS Code + Copilot, Claude, Codex, Cursor, …) — optional; the CLI works standalone.
Where to go next
- Quickstart — zero to a live scrape in five minutes
- Installation — every install path, one-liners included
- Agent Decision Guide — which tool for which task
- MCP Server — connect Claude, Cursor, or Copilot
- Browser Engines — which browser, how to handle a challenge
- Tools Reference — the 17-tool intent-based surface
- webrain vs Playwright — and other comparisons

