ツール

Browser automation CLI built for AI agents in native Rust: open pages, click and fill forms by refs from accessibility tree snapshots, read text and take screenshots, with compact snapshots and output limits to save context. From Vercel Labs; reuses local Chrome or installs one.

Browser automation plugin from Vercel Labs: agents drive Chrome through accessibility tree snapshots and element refs to navigate, click, fill forms and take screenshots, for web testing and exploratory QA. Install the agent-browser CLI first (npm, Homebrew or Cargo).

Browser automation MCP server open-sourced by ByteDance in the UI-TARS-desktop repo: drives pages through Puppeteer accessibility data with an optional vision mode, running locally over stdio or remotely over SSE or Streamable HTTP.

A Chrome extension that hands the browser you use every day to your agent, keeping your logins and settings, with screenshots, network monitoring, bookmarks and history, and semantic search over tab content. Install the extension and mcp-chrome-bridge first.

Community Playwright browser automation MCP from ExecuteAutomation (not Microsoft's official one): navigate, click, fill forms, screenshot and scrape page text, plus send HTTP requests, assert network responses and record actions into test code, with 143 device emulations built in.

Extracts any website's logo, colors, fonts, spacing, shadows and motion in one command, exporting W3C design tokens, a Tailwind theme, DESIGN.md or a brand guide PDF, plus WCAG contrast checks. Good for competitor and brand audits. Needs Node.js 18+; run dembrandt install-browser first.

Simon Willison's website screenshot CLI: batch screenshots from YAML, record demo videos, export PDF and HTML, run JavaScript in pages to extract data, and dump accessibility trees. Built on Playwright; install a browser on first use.

Crawls an entire site, counts words and keywords per page, and checks technical SEO such as titles, meta descriptions, image alt text, H1s and social tags. Outputs JSON by default or an HTML report for agents to act on. Needs Python; the optional AI content review needs an API key.

Clones websites: find the real source first or run browser recon, pick a path for static, React/Vue/Next or WebGL/Canvas/Three.js sites, strip trackers, check licenses, and verify against the original before swapping in your content. In Chinese; script paths assume the author's machine.

Browser Use's official plugin: connects the Browser Use MCP so Claude can drive your local Chrome or a cloud browser to browse, extract data, fill forms, test sites and take screenshots. Needs uv; cloud browsers need sign-in or an API key.