About Webrain
Webrain is an MCP server in the Scraping category: open-source Rust MCP server for LLM-driven browser automation and web scraping — one binary, three browser engines plus fast no-browser HTTP, 16 intent-based tools, any OS, any MCP client.
Install
git clone https://github.com/prokopis3/webrainThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (17)
webrain_batchSame op across many URLs in parallel tabs: `op` = fetch · extract · interact · eval · screenshot (+ `cdp_urls` per-proxy fan-out)
Parameters not published.
webrain_crawlSite traversal: `mode` = spider (BFS/DFS/best-first + autothrottle + checkpoint) · sitemap · scan · validate
Parameters not published.
webrain_downloadFiles/media: `engine` = http (stream) · ytdlp (HLS/playlists)
Parameters not published.
webrain_evalArbitrary JS in the page (escape hatch)
Parameters not published.
webrain_eval_in_frameRun JS inside a cross-origin iframe (isolated world)
Parameters not published.
webrain_extractStructured data: `mode` = schema (CSS) · regex · jsonld · table · autoschema · bm25
Parameters not published.
webrain_guideAgent decision guide (browser/challenge/extraction/delegation)
Parameters not published.
webrain_interactDrive the page: `action` = click · click_coords · type · press · scroll · nav · tab · select · hover · check · dialog · wait · upload · dismiss_overlays · add_init_script
Parameters not published.
webrain_navigateGo to a URL — page state + `challenge` / `crippled` detection. The entry point.
Parameters not published.
webrain_observeRead the current page: `what` = state · a11y · semantic · html · images · console · flatten (Shadow DOM) · fit · clean · screenshot · pixel · page_info · annotate · media
Parameters not published.
Show all 17 tools
webrain_pdfPDF work: `op` = page · extract (→ markdown) · render (→ vision tiles) · images
Parameters not published.
webrain_scrapeNo-browser HTTP fetch of one URL (10–100× faster, static only)
Parameters not published.
webrain_searchWeb search (duckduckgo · google · bing · brave)
Parameters not published.
webrain_serpStructured JSON search: `position`/`title`/`url`/`domain`/`snippet` across duckduckgo · bing · google · brave · auto (dedupe · paginate · region-pin · proxy · 2captcha)
Parameters not published.
webrain_sessionBrowser/auth/session: `op` = open · close · list · cookies · setcookies · save_state · restore_state · profiles · login · close_launch
Parameters not published.
webrain_visionScreenshot-tile vision index: `op` = index · retrieve
Parameters not published.
webrain_watchVideo → timestamped transcript + frames (no browser; `vision:true` → text captions)
Parameters not published.
Ask AI
Ask AI about Webrain
Powered by Claude · Grounded in docs
Security checks
6 checks have not been run yet.