CloudBrowser

Give AI agents a real cloud Chrome browser: open sessions, navigate, read pages, click, type, run scripts and take screenshots. Watch live or take over.

View on cloudbrowser.ai

Hosted MCP Server

npx add-mcp 'https://mcp.cloudbrowser.ai'

Installs into Claude Code, Codex, Cursor and more

Documentation

One URL. Every AI that speaks MCP.

Add CloudBrowser once and your assistant gets 20 browser tools — in chat, in your editor or inside your own agents.

https://mcp.cloudbrowser.ai

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.

Open ChatGPT

Create app

NameCloudBrowser

MCP server URLhttps://mcp.cloudbrowser.ai

AuthenticationOAuth

Create

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.

Your assistant thinks. CloudBrowser browses.

The Model Context Protocol lets an AI client discover tools and call them. CloudBrowser turns each call into real actions in an isolated Chrome — and hands back exactly what the model needs.

Your AI client
ChatGPT, Claude, Cursor, VS Code, Codex or your own agent decides which tool to call.
mcp.cloudbrowser.ai
Checks your account, runs the tool and returns page text, elements or a screenshot.
Isolated Chrome
A real browser with stealth fingerprints, a premium proxy, saved sessions and a live remote desktop.

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_browser Open a stealth Chrome browser in the cloud
connect_to_browser Take direct control of a browser
get_browsers List active browsers
get_connected_browsers List browsers under control
disconnect_browser Release control of a browser
close_browser Close 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_url Go to any URL and wait for it to load
get_page_content Read the title, text, headings, links and forms
get_elements Extract elements that match a CSS selector
take_screenshot Capture the viewport or the full page

Act like a person

Click, type and run scripts to search, filter, fill forms and move through flows.

click_element Click buttons, links and menus
type_text Type into inputs and forms
evaluate_script Run JavaScript on the page

Stay in control

Watch live, step in when a human is needed and reuse signed-in sessions.

start_remote_desktop Open a live view of the browser
stop_remote_desktop Close the live view
detect_captcha Spot reCAPTCHA, hCaptcha and Turnstile
browser_workspace Show browsers and sessions in a workspace
get_saved_sessions List saved sessions
resume_saved_session Reopen a saved session, still signed in
remove_saved_session Delete a saved session

Every tool, every parameter.

Each tool also tells the client whether it only reads or can change something, so assistants can ask you before they act.

Tool	What it does	Parameters	Type
`open_browser`	Open a stealth Chrome browser in the cloud.	label, keepOpen (300 s), saveSession, recoverSession, browser (Chrome · Chromium · Headless Shell), headless, stealth, args	Manages browsers
`connect_to_browser`	Take control of a running browser for page actions.	browserAddress, sessionId	Manages browsers
`get_browsers`	List the browsers running in your account.	—	Read-only
`get_connected_browsers`	List the browsers this conversation controls.	—	Read-only
`disconnect_browser`	Release control of a browser without closing it.	sessionId	Manages browsers
`close_browser`	Close a browser so its usage stops.	address	Closes or deletes
`navigate_to_url`	Go to a URL and wait until it has loaded.	sessionId, url, waitUntil (load · domcontentloaded · networkidle0 · networkidle2), detectCaptcha	Acts on pages
`get_page_content`	Read the page: title, URL, text, headings, links, forms, buttons and images.	sessionId	Read-only
`get_elements`	Return the elements that match a CSS selector.	sessionId, selector	Read-only
`take_screenshot`	Capture the 1920 × 1080 viewport or the full page.	sessionId, fullPage, type (png · jpeg)	Read-only
`click_element`	Click a button, link or menu item.	sessionId, selector	Acts on pages
`type_text`	Type into an input or text area.	sessionId, selector, text, clear (true)	Acts on pages
`evaluate_script`	Run JavaScript on the page and return the result.	sessionId, script	Acts on pages
`detect_captcha`	Spot reCAPTCHA, hCaptcha and Turnstile widgets on the page.	sessionId	Read-only
`start_remote_desktop`	Start a live view of a browser so a person can watch or take over.	address	Manages browsers
`stop_remote_desktop`	Stop the live view.	address	Manages browsers
`browser_workspace`	Show running browsers and saved sessions in a visual workspace, in clients that render MCP Apps.	browserAddress (optional)	Read-only
`get_saved_sessions`	List saved sessions by label.	—	Read-only
`resume_saved_session`	Reopen a saved session with its cookies and storage — still signed in.	label, requestId	Manages browsers
`remove_saved_session`	Delete a saved session.	label	Closes or deletes

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

Powerful tools, tightly scoped.

Connections are tied to your CloudBrowser account, scoped to browser control and easy to revoke.

OAuth 2.1 with PKCE

Clients that support OAuth register themselves and send you to CloudBrowser to sign in and approve browser control. No token to copy.

Bearer tokens for developers

Developer tools and agent frameworks can send your API token instead. Keep it in an environment variable on the server, never in client code.

Short-lived access

OAuth access tokens expire after 10 minutes and refresh tokens rotate on every use. A grant lasts up to 30 days.

Revoke in one click

See and revoke connected assistants in your dashboard. Revoking stops further tool calls.

Isolated per account

Each browser runs in its own container, and callers only ever see the browsers and sessions of their own account.

Read and write hints

Every tool declares whether it is read-only or can change things — clients use these hints to ask before acting.

Manage connected assistants Privacy policy

Use the URL — or run it yourself.

The connector is open source. Most people use the hosted server; the npm package is there when a client only speaks stdio.

Topic	npm package	Hosted (recommended)
Setup	npx @cloudbrowser/mcp-server	Paste https://mcp.cloudbrowser.ai into your client
Transport	stdio, or HTTP with --transport http	Streamable HTTP
Sign-in	CLOUDBROWSER_API_TOKEN environment variable	OAuth or Bearer API token
Works in web apps	Local desktop and CLI clients only	ChatGPT, Claude and other web clients
Updates	Can lag behind the hosted server	Always the newest tools
Browsers	The same cloud browsers	Cloud browsers in your CloudBrowser account

Use it from the OpenAI Agents SDK or Claude Agent SDK The CloudBrowser plugin for ChatGPT

What will your agent do today?

Once CloudBrowser is connected, these work as plain prompts in ChatGPT, Claude, Cursor or any MCP client.

Research

“Open the pricing pages of our five main competitors and summarize every plan change in a table.”

navigate_to_url get_page_content

Lead lists

“Find dental clinics in Austin that offer online booking and collect name, website and phone number.”

navigate_to_url get_elements

Price checks

“Check these three product pages and tell me which one is cheapest right now, with screenshots.”

navigate_to_url take_screenshot

“Walk through the signup flow on our staging site and screenshot each step. Flag anything that breaks.”

click_element type_text

Back office

“Sign in to the supplier portal with my saved session and list last month’s invoices.”

get_saved_sessions get_elements

Content

“Collect the ten latest posts from this blog and turn them into a Markdown digest.”

get_page_content evaluate_script

Questions, answered.

Explore the documentation

What is the CloudBrowser MCP server?

A hosted Model Context Protocol server at https://mcp.cloudbrowser.ai. It gives AI assistants 20 tools to open, drive and read real Chrome browsers running in the cloud.

Which clients can use it?

ChatGPT (developer mode), Claude (custom connectors), Claude Code, Cursor, VS Code, Codex, Gemini CLI, n8n and any other client that supports Streamable HTTP MCP servers. A dedicated CloudBrowser plugin for ChatGPT is coming soon.

How does authentication work?

Clients that support OAuth let you sign in with your CloudBrowser account and approve browser control. Developer tools can send your API token as an Authorization: Bearer header instead — find your token in the CloudBrowser dashboard.

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.

Can I run it locally instead?

Yes. The @cloudbrowser/mcp-server npm package runs over stdio with your CLOUDBROWSER_API_TOKEN. The npm release can lag behind the hosted server, so we recommend the hosted URL.

How is it different from a local browser MCP server like Playwright MCP?

Local browser MCP servers drive a browser on your own machine. CloudBrowser runs each browser in an isolated cloud container with stealth fingerprints, a premium proxy, saved sessions and a live remote desktop — and it works in web apps such as ChatGPT and Claude, where a local browser is not available.

What happens when a site asks for a login or a CAPTCHA?

detect_captcha flags CAPTCHA widgets so the agent can pause, and start_remote_desktop opens a live view where you can step in. Saved sessions let agents return to sites you are already signed in to.

How many browsers can an agent run?

As many as your plan allows at once: 10 concurrent browsers on Basic and 25 on Premium, each with up to 3 tabs. Custom plans go higher.

Can I use it from my own agent code?

Yes. The OpenAI Agents SDK, the Claude Agent SDK, the OpenAI Responses API and other MCP-capable frameworks can call the hosted server with a Bearer token. See the SDK page for ready-to-run examples.

Does the agent see my passwords?

No. Sign in yourself on the live remote desktop and save the session; the agent resumes it later with resume_saved_session. Cookies and storage stay in your CloudBrowser account.

Put a real browser in your agent’s loop.

Start with a 7-day free trial. Connect ChatGPT, Claude or your code in minutes.