#chrome

A MCP server that provides Chrome DevTools Protocol access to LLMs

A chrome extension bridge that allows you to connect to a mcp server to use global window object.

An MCP server to allow you to debug webpages using LLMs

Servidor MCP para integração entre extensão Chrome e Claude AI

Cursor Model Context Protocol (MCP) extension for Chrome - with comprehensive test coverage

Allow LLMs to control a browser with Browserbase and Stagehand

Chrome Extension MCP Server implemented in Go - For Model Context Protocol to interact with Chrome extensions

Pick any element on any webpage and send its HTML, CSS, React props, console logs, and network context to Claude Code, Cursor, or Windsurf via MCP — in one click.

🚀 The ONLY browser automation that bypasses Cloudflare, antibots, and social media blocks. Supercharge any MCP-compatible AI agent with undetectable, real-browser automation. No CAPTCHAs. No blocks. Just results.⚡ 30-second setup • 🛡️ Undetectable by design • 🏆 98.7% success rate on protected sites • 🕵️ Full network debugging via AI chat Features: Works on protected sites that block traditional automation- Pixel-accurate element cloning via Chrome DevTools Protocol - Full network debugging through AI chat — see every request, response, header, and payload- Your AI agent becomes a network detective — no more guessing what APIs are being called- 🎛️ Modular architecture — disable unused sections, run minimal installs- ⚡ Lightweight deployments — from 21 core tools to full 88-tool arsenal- Clean MCP integration — no custom brokers or wrappers needed- 88 focused tools organized into 11 logical sections

Let AI agents like ChatGPT & Claude use real-world local/remote tools you approve via browser extension + optional MCP server

Connect Claude Code, Cursor, and any MCP client to your real Chrome browser. Real sessions, real cookies, no headless conflicts. Works alongside your browser — no profile fights, no fresh sessions.

Control Google Chrome browser tabs, windows, and navigation

Developer tool suite enabling Claude Desktop, Claude Code, and other MCP hosts like Cursor, to interact with claude.ai in Chrome browsers.

Rip any YouTube transcript. Clean text, structured JSON, or Markdown for AI agents.

Headless browser for AI agents. Fetches web pages and returns a structured Semantic Object Model (SOM) instead of raw HTML - 17x fewer tokens on average. 13 MCP tools including fetch, click, type, scroll, and extract.

Open-source MCP server with 40+ browser automation tools, YAML workflow engine, and installable domain knowledge packs. Includes Chrome extension for real DOM access, REST API, and Svelte dashboard. Works with Claude Code, Cursor, Claude Desktop, and any MCP client.

B4n1Web is an ultra-lightweight agentic browser engine (5MB) for AI agents. It provides three browsing modes: Light (HTTP fetch + HTML parsing), JS (JavaScript extraction), and Render (full headless browser with screenshots). Perfect for web scraping, data extraction, E2E testing, and autonomous AI agents that need to navigate and extract content from websites without the overhead of a full browser. Features: Ultra-lightweight binary (<10MB) Python SDK available on PyPI MCP server for integration with Claude, Cursor, OpenCode, Windsurf, Antigravity SQLite-based SecurityShield for safe browsing Multiple modes: Light, JS, Render MCP Server: Command: b4n1web mcp -p 8080 Port is configurable — change 8080 to any available port Tools: goto (navigate & extract content), get_links (extract all links from current page)

A Model Context Protocol (MCP) server that enables AI assistants to interact with web browsers and mobile applications using WebDriverIO. Automate Chrome browsers, iOS apps, and Android apps—all through a unified interface.

100-tool browser automation for AI agents via MCP. Screenshots, DOM inspection, network capture, form filling, cookie management, tab orchestration, session recording, and structured data extraction via Chrome extension. One-command setup: npx crawlio-browser init auto-configures 14 MCP clients.recording + 1 compiler) with framework-aware intelligence, typed evidence infrastructure, and confidence-tracked findings — captures what static crawlers can't see.