CloudBrowser runs real Chrome in the cloud so ChatGPT, Claude and your own agents can browse, click, type and pull data from any website — while you watch live and take over anytime.
Screen recording of a real Chrome session: an AI agent is asked to “Add a sweater that fits my 30 lb dog to my cart”. It opens demo.vercel.store, closes a popup, searches for “dog sweater”, opens the product, reads the size options, picks 20 – 50 lbs and adds it to the cart.
Acme Store
demo.vercel.store
TaskAdd a sweater that fits my 30 lb dog to my cart
navigate_to_urldemo.vercel.store
TaskAdd a sweater that fits my 30 lb dog to my cart
Works with the AI tools you already use
ChatGPT
Claude
Cursor
VS Code
Codex
Gemini CLI
Claude Code
n8n
Make
How it works
From prompt to real browser in three steps.
mcp.cloudbrowser.ai
01
Connect
Paste one URL into ChatGPT, Claude or your IDE — or call the API. Sign in with your CloudBrowser account or use an API token.
Compare flight prices for Friday and screenshot the cheapest.
02
Ask
Describe the task in plain words. Your agent opens a cloud browser and picks the right tools to get it done.
Live
03
Watch & step in
Follow along on a live remote desktop. When a login or CAPTCHA needs a human, take over — then hand it back.
Model Context Protocol
One URL. Every AI that speaks MCP.
Add CloudBrowser once and your assistant gets 18 browser tools — in chat, in your editor or inside your own agents.
https://mcp.cloudbrowser.ai
Sign in with your CloudBrowser account (OAuth) or send your API token as a Bearer header. Use the URL exactly as shown.
Add CloudBrowser to ChatGPT
On ChatGPT for the web, turn on Developer mode in Settings.
Open Apps (or Plugins, depending on your account) and create a new app named CloudBrowser with the MCP server URL.
Choose OAuth authentication, create it and sign in with your CloudBrowser account.
In a chat, open the + menu → Developer mode and select CloudBrowser.
Developer mode is a ChatGPT beta for eligible paid plans on the web; in Business workspaces an admin sets it up. Menu names vary between ChatGPT releases.
The open-source MCP connector is free. Browser usage requires a CloudBrowser account and a paid plan after the 7-day Basic trial. Get your API token in the dashboard.
18 MCP tools
Everything a browser can do, as tools.
Your assistant decides what to call. CloudBrowser runs each step in a real browser and returns what the agent needs — page content, elements or a screenshot.
Launch & manage
Spin up isolated Chrome instances on demand and keep track of every session.
open_browserOpen a remote browser in the cloud
connect_to_browserTake direct control of a browser
get_browsersList active browsers
get_connected_browsersList browsers under control
disconnect_browserRelease control of a browser
close_browserClose a browser when the job is done
Navigate & read
Load any page, including JavaScript-heavy apps, and read what a person would see.
navigate_to_urlGo to any URL
get_page_contentRead the HTML of the current page
get_elementsExtract elements that match a selector
take_screenshotCapture the page as an image
Act like a person
Click, type and run scripts to search, filter, fill forms and move through flows.
click_elementClick buttons, links and menus
type_textType into inputs and forms
evaluate_scriptRun JavaScript on the page
Stay in control
Watch live, step in when a human is needed and reuse signed-in sessions.
start_remote_desktopOpen a live view of the browser
stop_remote_desktopClose the live view
detect_captchaSpot CAPTCHA widgets on the page
get_saved_sessionsList saved sessions
remove_saved_sessionDelete a saved session
Human in the loop
Watch it live. Take the wheel anytime.
Every browser can stream to a live remote desktop. When an agent meets a login, a one-time code or a CAPTCHA, you step in — and it carries on from there.
Live remote desktop on every plan
detect_captcha tells the agent when to ask for help
Saved sessions keep agents signed in
Tag browsers and find them in your dashboard
Live view · browser 7f3aLive
Sign in to continueI’m not a robot
detect_captcha CAPTCHA found — agent pausedYou took over the live viewSolved — agent resumed the task
Built for production
Built for the web as it really is.
Real sites have logins, heavy JavaScript and bot checks. CloudBrowser is made for all of it.
Real Chrome, isolated
Every browser runs in its own isolated container, separate from every other session.
Human-like fingerprints
Browser fingerprints match real-world devices — timezone, locale, WebGL and screen — to keep bot flags down.
Premium proxies included
Route traffic through premium proxies on every plan, or bring your own when you need a specific network.
Sessions that stay signed in
Save and restore cookies and localStorage so agents pick up exactly where they left off.
Up to 25 browsers at once
Run 10 concurrent instances on Basic and 25 on Premium, with up to 3 tabs each.
Works with your code
Connect over CDP with Puppeteer, Playwright or Selenium, or use the Node.js, Python and .NET clients.
For developers
Prefer code? It’s just Puppeteer.
Open a browser with one API call, then connect over CDP with the tools you already know. Official clients for Node.js, Python and .NET.
Any client that supports remote MCP servers: ChatGPT, Claude, Claude Code, Cursor, VS Code, Codex, Gemini CLI, n8n and more. Add one URL — https://mcp.cloudbrowser.ai — and the assistant gets CloudBrowser’s browser tools.
Is the MCP server free?+
The open-source MCP connector is free, and it adds no AI inference charge. Browser usage requires a CloudBrowser account and a paid plan after the 7-day Basic trial.
Do I need to write code?+
No. You can connect ChatGPT or Claude with a URL, manage browsers from the dashboard, or build visual workflows in n8n. Developers can use the HTTP API, Puppeteer and our client libraries.
How is browser usage measured?+
One usage unit is 30 seconds of browser time per tab, so two tabs open for one minute use four units. Basic includes 30,000 units a month and Premium 120,000. The usage calculator helps you estimate.
Can I watch what the agent is doing?+
Yes. Live remote desktop is included on every plan. Open it from the dashboard or let your agent start it with start_remote_desktop, then step in whenever a human is needed.
How do agents stay logged in to websites?+
Browsers can save their session — cookies and localStorage — and reuse it later, so an agent can return to a site you have already signed in to.
Put a real browser in your agent’s loop.
Start with a 7-day free trial. Connect ChatGPT, Claude or your code in minutes.