Add dmytrome/groundhog to Browser Automation

README.md

@@ -416,6 +416,7 @@ Web content access and automation capabilities. Enables searching, scraping, and
 - [Cubenest/rrweb-stack](https://github.com/Cubenest/rrweb-stack) [![Cubenest/rrweb-stack MCP server](https://glama.ai/mcp/servers/Cubenest/rrweb-stack/badges/score.svg)](https://glama.ai/mcp/servers/Cubenest/rrweb-stack) 📇 🏠 - Local-first MCP server (@peekdev/mcp) + Chrome extension that records your real authenticated browser session (rrweb DOM + console + network, PII-masked, to local SQLite) and lets AI coding agents query it or drive the browser. No cloud, no telemetry.
 - [Custodia-Admin/pagebolt-mcp](https://github.com/Custodia-Admin/pagebolt-mcp) [![Custodia-Admin/pagebolt-mcp MCP server](https://glama.ai/mcp/servers/Custodia-Admin/pagebolt-mcp/badges/score.svg)](https://glama.ai/mcp/servers/Custodia-Admin/pagebolt-mcp) 📇 ☁️ - MCP server for screenshots, PDFs, OG images, and narrated video recording from Claude Desktop, Cursor, and Windsurf.
 - [dashi96/chromium-bridge](https://github.com/dashi96/chromium-bridge) [![dashi96/chromium-bridge MCP server](https://glama.ai/mcp/servers/@dashi96/chromium-bridge/badges/score.svg)](https://glama.ai/mcp/servers/@dashi96/chromium-bridge) 📇 🏠 🍎 🪟 🐧 - MCP server + Chrome extension that connects Claude Code to Chromium-based browsers (Arc, Vivaldi, Brave) where the official Claude in Chrome extension doesn't work — navigate, click, read pages, run JS, and record GIFs in the user's real browser.
+- [dmytrome/groundhog](https://github.com/dmytrome/groundhog) [![dmytrome/groundhog MCP server](https://glama.ai/mcp/servers/dmytrome/groundhog/badges/score.svg)](https://glama.ai/mcp/servers/dmytrome/groundhog) 🐍 🏠 🍎 🪟 🐧 - Web search, read and research over a real stealth-patched Chrome, driven by raw CDP so the `Runtime` domain is never enabled and the `isAutomatedWithCDP` tell is absent. Strips text that is invisible in the rendered DOM before the model reads it and reports each occurrence in `threats`, returns a SHA-256 provenance receipt per source, and re-checks the SSRF guard after redirects. `research` ranks passages across all sources in one pass — extracts, not summaries, so no model or API key is involved. MIT.
 - [eat-pray-ai/yutu](https://github.com/eat-pray-ai/yutu) 🏎️ 🏠 🍎 🐧 🪟 - A fully functional MCP server and CLI for YouTube to automate YouTube operation
 - [executeautomation/playwright-mcp-server](https://github.com/executeautomation/mcp-playwright) 📇 - An MCP server using Playwright for browser automation and webscrapping
 - [eyalzh/browser-control-mcp](https://github.com/eyalzh/browser-control-mcp) 📇 🏠 - An MCP server paired with a browser extension that enables LLM clients to control the user's browser (Firefox).