kpfkpbkijebomacngfgljaendniocdfp
Browser automation for Claude without token limits. Uses CSS selectors, not snapshots. Open source, zero telemetry. Give Claude Code (and other AI assistants) direct control of your real Chrome browser Stop wrestling with headless browsers, bot detection, and authentication flows. Blueprint MCP for Chrome bridges the Model Context Protocol (MCP) with your actual Chrome browser - keeping you logged into all your sites, preserving your extensions, and using your real browser fingerprint. THE CRITICAL ADVANTAGE: Efficient browser automation that does not consume your AI's context. Instead of sending massive page snapshots with every action (which quickly exhausts context limits and often exceeds MCP response size limits), Blueprint MCP lets your AI interact directly - click, type, navigate - and only fetch page content when specifically needed. This enables complex, multi-step workflows that would be impossible with snapshot-based approaches. Perfect for developers using Claude Code, Claude Desktop, Cursor, or any MCP-compatible AI client who need to automate web tasks without the headaches of Playwright/Puppeteer/Selenium. The problem: Traditional browser automation requires sending full page snapshots after every action, consuming thousands of tokens per interaction and hitting response size limits. You also lose logged-in sessions, face bot detection, and spend time configuring browser profiles. The solution: Blueprint MCP connects your AI assistant to your real Chrome browser through direct commands. Your AI controls the browser - click, type, navigate - without needing page snapshots unless explicitly requested. This preserves context for actual decision-making instead of wasting it on redundant page content. What this enables: - AI-powered web scraping that bypasses bot detection - Automated form filling with your saved passwords - Testing workflows using your logged-in accounts - Content extraction from authenticated sites - Browser automation that works with 2FA and CAPTCHAs Real Browser Automation: - Uses your actual Chrome profile - Stays logged into Gmail, GitHub, AWS, etc. - Stealth mode - No bot detection. Uses your real browser fingerprint - Extension support - Works alongside your existing Chrome extensions - Session persistence - No re-authentication needed Native MCP Integration: - 20+ browser tools exposed via Model Context Protocol - Tab management - Create, switch, close tabs programmatically - DOM inspection - Get accessible page content - Network monitoring - Capture requests, replay with authentication - JavaScript execution - Run code in page context Developer Experience: - Zero setup - Install extension, works instantly - Auto-reconnection - Survives browser restarts - Debug mode - Verbose logging for troubleshooting - Status visibility - Real-time connection status Comprehensive Automation: - Screenshots (full page or elements) - Content extraction as Markdown - Form automation (fill, dropdowns, file uploads) - Mouse/keyboard control (click, type, hover, drag-drop) - Performance metrics (Web Vitals) Advanced Capabilities: - Tech stack detection (40+ frameworks) - Network request replay - PDF export - Dialog handling (alert/confirm/prompt) - Extension management Setup (3 steps, 2 minutes): 1. Install MCP server: npm install -g @railsblueprint/blueprint-mcp 2. Install this Chrome extension 3. Configure AI client: claude mcp add browser npx @railsblueprint/blueprint-mcp@latest The extension auto-connects when your AI client starts the MCP server. Free Tier (Local Mode): - All communication stays on your machine (localhost WebSocket) - Zero data sent to cloud - No tracking, telemetry, or analytics - Works completely offline - No account required Open Source: - Full source: https://github.com/railsblueprint/blueprint-mcp - Apache 2.0 license - Audit the code yourself Blueprint MCP for Chrome - Give your AI assistant the browser automation it deserves.
BrowserAgent - AI Agents in Browser
Run private, cost-free AI agents directly in your browser. Automate tasks, enhance browsing, and control your data with local AI. Unleash the power of AI agents directly in your browser with the BrowserAgent Chrome Extension! Built for BrowserAgent workflows, this extension lets you effortlessly export and run your custom AI agents entirely within Chrome. Experience true privacy, no cloud API costs, and seamless AI automation – all without leaving your browser. Start automating tasks and enhancing your browsing experience with local, powerful AI today.
Real Browser MCP
Let AI agents control your real browser - your tabs, your sessions, your logins Supporting Claude code, Codex, Cursor, Antrigravity, Windsurf and more! Give your AI access to ANY WEBSITE, make him your parner of web! Your AI agent writes code all day but can't see any of it in the browser. It finishes a task, says "please verify," and you become its eyes. Switch to Chrome, log in, click around, find the bug, go back. Repeat. Real Browser MCP fixes that. It's a Chrome extension + MCP server that connects your AI coding agent to the browser you already have open. Not a headless copy. Not a fresh Playwright instance. The one with your sessions, logins, and cookies already there. 1. Install this extension 2. Add the MCP server to your AI editor (Cursor, Claude Code, Windsurf, or any MCP client) 3. Your agent can now see and interact with your browser WHAT YOUR AGENT CAN DO - Take accessibility snapshots of any page (structured data, not screenshots) - Click buttons, fill forms, select dropdowns - Navigate to URLs and manage tabs - Take screenshots for visual verification - Read page text content - Run JavaScript in the page - Handle alert/confirm/prompt dialogs - Monitor console messages and network requests - Wait for elements to appear Playwright launches a blank browser. No cookies, no sessions, no logins. If your app is behind auth or corporate SSO, you have to replay the entire login flow every time. Real Browser MCP skips all that because it uses the browser you're already logged into. - Verify UI changes after code edits - Test authenticated flows without logging in again - Fill out forms and submit them - Debug layout issues by reading the DOM - Check production after deploy - Run QA steps without leaving your editor - Everything stays local. The extension talks to a localhost MCP server on your machine - No data sent anywhere. No analytics, no tracking - Fully open source: https://github.com/ofershap/real-browser-mcp - An MCP-compatible AI editor (Cursor, Claude Code, Windsurf, Cline, etc.) - Node.js 18+ - Run: npx real-browser-mcp to start the server
MCP-B Extension
AI-powered browser assistant with Model Context Protocol integration for enhanced web interactions This extension let's you call webmcp tools and script any website
MCP Chrome Extension - AI Browser Control
Turn Chrome into an MCP server. Let AI control your browser: navigate, click, fill forms, and take screenshots. The best MCP server for Chrome browser automation. Transform your Chrome browser into a fully-featured MCP (Model Context Protocol) server, enabling AI coding assistants to interact with your browser in real time. 📦 QUICK SETUP (3 steps) 1. Install the native bridge: npm install -g mcp-chrome-bridger Then run: mcp-chrome-bridger register Or pnpm install -g mcp-chrome-bridger Then run: mcp-chrome-bridger register 2. Load this extension and click "Connect" in the popup. 3. Add to your MCP client config (Claude Code / Cursor / Windsurf / Kiro / Cline etc), following the connection info shown in the popup: { "mcpServers": { "mcp-chrome": { "type": "http", "url": "http://127.0.0.1:12306/mcp" } } } ✨ KEY FEATURES - Navigate and control browser tabs programmatically - Take full-page or viewport screenshots - Extract and parse page content (text, HTML, DOM) - Interact with page elements — click, scroll, hover - Fill and submit forms automatically - Capture and inspect network requests - Search browsing history and bookmarks - Multi-tab management and coordination 🤖 COMPATIBLE AI CLIENTS Works with any MCP-compatible AI assistant: 🔒 PRIVACY & SECURITY This extension only communicates with a local native bridge on your own machine (127.0.0.1). No data is sent to external servers by the extension itself. 📖 OPEN SOURCE Full source code and documentation available on GitHub: https://github.com/femto/mcp-chrome ⚠️ REQUIREMENT: The mcp-chrome-bridger npm package must be installed on your system for full functionality.
