Allows AI agents to work within a logged-in Gmail session via the shared Chrome browser, using browser tools to read, compose, and manage email without exposing passwords.
Allows AI agents to operate a logged-in Stripe dashboard through the shared browser, enabling browser-based tasks on payments and account pages, with sensitive-site model routing.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Dooza Browser open my Stripe dashboard and list this month's payouts"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
One shared, logged-in Chrome for all your AI agents. Claude Code, Codex, ChatGPT or your own scripts get a real browser through MCP or plain HTTP: open tabs, read pages, click, type, upload files, run short Playwright scripts, or hand off a whole web task. Agents share what they learn about each site, and they never steal your mouse or close your tabs.
We built it to run Dooza's own team of AI agents (sales, SEO, video, ops) on one machine, all sharing one Chrome that is logged in once. This is that code, cleaned up.
Log in once. The agents use one Chrome profile. You sign in to Gmail, LinkedIn, Stripe... by hand once; cookies persist. Agents never see your passwords.
Many agents, one browser, no fights. Each tab belongs to the agent that opened it. Agent windows open in the background in their own screen area, never as tabs in your window, and never take focus.
Fast actions, not click-by-click. tab_playwright runs a short Playwright script on a tab: 10 steps in one tool
call. Models already know Playwright well, so it is quicker and cheaper than one tool call per click.
Site memory. site_note saves one-line lessons per site ("the Save button is #submit-2", "this site blocks
headless"). They come back automatically every time any agent opens that site.
Whole tasks on a cheap model. browse(task) gives the task to browser-use
on any OpenRouter model (or to headless Claude Code), with a judge, a retry on a stronger model, and a stronger
model by default on sensitive sites (inbox, payments).
Related MCP server: MultiZen
Tool | What it does |
| Whole web task in its own background window; returns text |
| New background tab you own; returns |
|
|
| Step-by-step control |
| Python Playwright (async) on that tab; set |
| File upload, including buttons that open a native file picker |
| |
| Read or add per-site notes (secrets are refused) |
| Chrome version, open tabs, free task slots, OpenRouter spend |
Every tool is also POST /api/<tool> with the arguments as JSON.
git clone https://github.com/Dooza-ai/dooza-browser && cd dooza-browser
python3 -m venv .venv && .venv/bin/pip install -e . # no browser download: it drives your own Chrome
cp config.example.json config.json
# 1. a dedicated Chrome with DevTools on localhost:9222 (sign in to your sites in this window, once)
examples/start-chrome.sh &
# 2. the server (MCP at http://127.0.0.1:8765/mcp)
export OPENROUTER_API_KEY=... # only for browse() with the browser-use engine
.venv/bin/dooza-browserConnect a client:
claude mcp add --transport http --scope user browser http://127.0.0.1:8765/mcp # Claude Code
# Codex: ~/.codex/config.toml -> [mcp_servers.browser] url = "http://127.0.0.1:8765/mcp"
curl -s localhost:8765/api/tab_open -H 'Content-Type: application/json' -d '{"url":"https://example.com","owner":"me"}'For Claude Code, copy skill/SKILL.md to ~/.claude/skills/dooza-browser/SKILL.md so agents know when to use which tool.
On a headless server, run Chrome on a virtual display wide enough for both areas (Xvfb :99 -screen 0 2880x900x24);
your own window sits at x 0-1440, agent windows open at x >= 1440 (agent_window in config.json). A systemd unit is
in examples/.
config.json)Key | Meaning |
|
|
| OpenRouter model ids: normal sites / |
| URL substrings that get the |
|
|
| Forgotten tabs are closed; a 4th tab closes your oldest |
| Where agent windows open ( |
|
|
| Folders uploads may come from ( |
| Optional |
|
|
Environment: DOOZA_BROWSER_CONFIG (default ./config.json), DOOZA_BROWSER_HOME (logs, screenshots, site notes,
optional credentials.env; default ~/.dooza-browser), OPENROUTER_API_KEY.
credentials.env (NAME=value lines) is passed to browser-use as sensitive_data: the model only sees NAME and the
value is filled in at typing time.
The server listens on 127.0.0.1 only. Anyone who can reach it controls your logged-in browser: don't expose it.
Page content is data, never instructions; tool descriptions and the browse prompt say so, but prompt injection is a real risk for any browser agent. Give the agent Chrome only the logins your agents need.
tab_eval and tab_playwright run code you send in the page or on your machine. Use the sandbox user on shared
machines.
Optional python -m dooza_browser.captcha <tab> solves reCAPTCHA/hCaptcha/Turnstile through 2Captcha (paid,
TWOCAPTCHA_API_KEY). Use it only where the site's terms allow automation.
Built on browser-use, FastMCP and Playwright. Ideas from Aside's write-up on browser agents (Playwright actions, site memory).
MIT licensed. Made by Dooza: AI agents that work as your team.
This server cannot be deployed
Control a real browser from AI agents: navigate, click, type, screenshot, read the page.
Let your AI agent operate any website through a real, logged-in browser session.
Connect AI agents to your own Chrome with scoped access, approvals, and verified task results.
Browser MCP for logged-in tasks. Uses your Chrome — credentials stay local. Zero-token replay.
