Real Browser MCP
ofershap/real-browser-mcp
Agente IA vê e controla seu navegador Chrome real com sessões ativas
Ver no GitHubMCP server que integra um agente de IA com seu navegador Chrome real, permitindo que o agente veja, navegue e interaja com páginas web mantendo sessões e logins existentes. Combina um servidor MCP com uma extensão Chrome para dar ao seu assistente IA visão e controle genuínos do navegador.
Instalação
npx convez-ai ofershap/real-browser-mcp1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Verificação de código em páginas web ao vivo com o agente
- Automação de tarefas web mantendo login e contexto
- Debugging de aplicações web com agente navegando como usuário real
- Testes end-to-end com IA interagindo com interface do navegador
Veredito

Ferramenta diferenciada que fecha um gap crítico: permite que agentes IA vejam e manipulem o navegador real em vez de fazer web scraping cego. Especialmente útil para verificação de deployments e testes de aplicações web, com integração direta no Cursor.
README
A tradução para o português deste README ainda está na fila.
You ship a fix. Your agent says "done, please verify." You alt-tab to Chrome, navigate to the page, log in, click around, find the bug.
Your agent just wrote the code. It could also verify it. It already has your browser open right there. It just can't see it.
Now it can.
Quick Start
Two parts:
- MCP server - runs on your machine, talks to your AI agent
- Chrome extension - sits in your browser, executes the commands
1. Add the MCP server
Cursor (one click):
Or add manually in Cursor Settings > MCP > "Add new MCP server":
{
"mcpServers": {
"real-browser": {
"command": "npx",
"args": ["-y", "real-browser-mcp"]
}
}
}
Claude Desktop: Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows). Add the same JSON block.
Windsurf: Settings > MCP. Same config.
Any MCP-compatible client works.
2. Install the Chrome extension
Or load from source:
git clone https://github.com/ofershap/real-browser-mcp.git
- Open
chrome://extensionsand enable Developer mode (toggle in the top right) - Click Load unpacked and select the
extension/folder from the cloned repo
Click the Real Browser MCP icon in your toolbar.
Green dot = connected. Gray = waiting for server.
Done. Your agent can see your browser.
How Others Compare
| Real Browser MCP | Playwright MCP | Chrome DevTools MCP | |
|---|---|---|---|
| Uses your existing browser | Yes | No, launches new | Partial, needs debug port |
| Sessions and cookies | Already there | Fresh profile | Manual setup |
| Works behind corporate SSO | Yes | No | Depends |
| Setup | Extension + MCP config | Headless browser | Chrome with --remote-debugging-port |
🧠 Teach Your Agent
The agent can use all 18 tools out of the box, but it works better when it knows when and how to chain them. A config file teaches the right workflow - snapshot first, then act, then verify.
Run one command:
npx real-browser-mcp --setup cursor
This installs:
~/.cursor/rules/real-browser-mcp.mdc- teaches the snapshot-first workflow, how to handle dropdowns, when to use screenshots vs snapshots~/.cursor/commands/check-browser.md- adds/check-browserto your Cursor chat
After that, type /check-browser in any chat. Or just say "check the result in my browser" and the agent knows what to do.
npx real-browser-mcp --setup claude
Adds an AGENTS.md to your project root. Claude Code auto-discovers it.
See agent-config/ for manual installation or to customize the rules.
What It Can Do
18 tools. Grouped by purpose.
See
| Tool | What it does |
|---|---|
browser_snapshot | Accessibility tree with element refs. Compact mode (default) returns only interactive elements |
browser_screenshot | Capture what's on screen |
browser_text | Extract raw text from page or element |
browser_find | Query elements by CSS selector |
Interact
| Tool | What it does |
|---|---|
browser_click | Click by ref or CSS selector |
browser_click_text | Click by visible text. Works through React portals and overlays |
browser_type | Type into inputs and contenteditable fields |
browser_press_key | Key combos (Enter, Escape, Ctrl+A) |
browser_scroll | Scroll pages and virtual containers |
browser_hover | Trigger tooltips and dropdowns |
browser_select | Pick from native <select> dropdowns |
browser_wait | Wait for elements to appear or disappear |
Navigate
| Tool | What it does |
|---|---|
browser_navigate | Go to a URL in the active tab |
browser_tabs | List, create, close, or focus tabs |
Debug
| Tool | What it does |
|---|---|
browser_console | Console output (log, warn, error) |
browser_network | XHR/fetch requests with status codes |
browser_evaluate | Run JavaScript via Chrome DevTools Protocol |
browser_handle_dialog | Handle alert/confirm/prompt dialogs |
Configuration
| Env var | Default | What it does |
|---|---|---|
WS_PORT | 7225 | WebSocket port for extension connection |
Connection drops are handled automatically with exponential backoff (1s to 30s), ping/pong health checks every 10s, and per-tool timeouts (5s for clicks, 60s for navigation).
Run two server instances on different ports:
{
"mcpServers": {
"browser-work": {
"command": "npx", "args": ["-y", "real-browser-mcp"]
},
"browser-personal": {
"command": "npx", "args": ["-y", "real-browser-mcp"],
"env": { "WS_PORT": "9333" }
}
}
}
Update the port in each extension popup to match.
Everything stays on your machine. The extension connects to the MCP server via WebSocket on localhost. No cloud, no proxy, nothing leaves your browser.
real-browser-mcp/
├── mcp-server/ MCP server (npm package, TypeScript)
│ └── src/tools/ One file per tool, registry pattern
├── extension/ Chrome extension (Manifest V3, plain JS)
│ ├── background.js Service worker, WebSocket client, tool handlers
│ ├── content.js Console capture
│ └── popup/ Connection status UI
├── agent-config/ Pre-built configs for Cursor + Claude Code
│ ├── cursor/ Rules and commands
│ ├── skills/ Browser automation skill
│ └── setup.mjs One-command installer
└── tests/ Bridge + registry tests
Stack: TypeScript (strict) · MCP SDK · WebSocket · Chrome Extension Manifest V3 · Vitest
git clone https://github.com/ofershap/real-browser-mcp.git
cd real-browser-mcp
npm install
npm run build
npm test
| Command | What it does |
|---|---|
npm run build | Compile TypeScript |
npm run dev | Watch mode |
npm test | Run tests |
npm run typecheck | Type check without emitting |
npm run setup:cursor | Install Cursor rule + command |
FAQ
That's the whole point. The extension runs inside your actual Chrome - same cookies, same sessions, same local storage. No re-authentication needed.
No. The MCP server and extension talk over WebSocket on localhost. Nothing leaves your machine. There's no analytics, no telemetry, no cloud component. Privacy policy.
Any MCP-compatible client. Cursor, Claude Desktop, Claude Code, Windsurf, Cline, and anything else that speaks the MCP protocol.
Yes. Run two MCP server instances on different ports. See Configuration for the setup.
They launch a new browser instance from scratch - no state, no cookies, no sessions. You have to replay the full login flow every time. This connects to the browser you already have open with everything already loaded.
Contributing
Bug reports, feature requests, and PRs welcome. Open an issue first for larger changes.
Author
README built with README Builder