unbrowser by Unchained
Chrome-free MCP web access for agents with low-token page maps and browser escalation hints.
GitHub から自分のパソコンにインストールして使うオープンソースのプログラムです。スター、週間ダウンロード数、注目の伸びを確認できます。
利用スコア順:GitHubスター、週あたりのダウンロード数、最近のリリース、エンドポイントの応答。よく使われている=一番良い、ではありません。 スターがひとつもないまま大量に登録している発行者はこのタブに出ません。「すべて」で検索すると見つかります。
カードの見方:↓ 週あたりのダウンロードi★ GitHubスターi3つの柱:レビュー · チェック · 利用状況i更新=最新バージョンをレジストリに公開した日i
Chrome-free MCP web access for agents with low-token page maps and browser escalation hints.
A browser your AI agent remembers. Learn a site once, replay it in one call, zero model calls.
Check websites against the W3C Web Sustainability Guidelines and look up the guidelines
55 web-data tools for AI agents: jobs, news, tenders, laws, shopping, social, web pages, leads.
Local MCP for Power Automate with browser-backed auth, target locking, review diff, and rollback.
Turn HTML or mobile-learning exports into SCORM 2004/1.2 packages, and validate any SCORM zip.
Your real Chrome in background tabs (Windows; needs the NexusBrowser bridge and extension).
Jira and Confluence behind SSO via your own browser session: every mcp-atlassian tool, no API token
Extract a website's favicon URL (any size 16-512) via the free FaviconDL API. No API key.
Daily Product Hunt launches with makers, website, company domain, votes, and topics
Find a named page type on a company's own website from its domain, in 11 languages.
AI-powered browser automation MCP — 6 tools for web interaction, extraction, and validation.
Control Parallels Desktop VMs from MCP: power, screenshot, exec, keyboard, sequences. macOS only.
MCP bridge between Chromium browsers (Arc, Vivaldi, Brave) and Claude Code: browser automation
Stealth browser for AI agents: navigate, click, type and extract on bot-protected sites.
Consult existing Grok Bots from Codex and Claude Code using official Cursor browser login.
Read Bilibili, Douyin, Xiaohongshu and any web page via your own logged-in Chrome.
Hands your live Chrome tab to any MCP client — snapshot, navigate, click, type, extract.
Find the media stream behind any web page: browser-driven HLS/DASH/MP4 with learnable site profiles
Web data and proxies for agents: scrape to Markdown, SERP, crawl/map, unlocker, collectors, proxies.
Capture webpages as images or PDFs, or get them as Markdown, with Screenshot Scout.
Unofficial Radio MCP — wraps Radio Browser API (free, no auth)