MCP server · Browser automation

Chromium Bridge MCP server

Let your AI drive your Chromium browser: open tabs, click, read pages, and record GIFs.

Chromium Bridge connects your AI assistant to a Chromium-based browser like Arc, Vivaldi, or Brave. It is handy if you want your AI to actually open pages, click buttons, fill forms, and read what is on screen instead of just talking about it. You install a small browser extension plus a helper program, and then you can ask your AI to do browser tasks for you.

What is an MCP server? The 30-second version

On its own, your AI can only chat. An MCP server is a small helper program that gives your AI a new skill or a connection to an app. This one connects your AI to your Chromium browser, so it can look at tabs, read pages, and click things when you ask. You do not need to understand how it works inside; you just install it once and then talk to your AI like usual.

What this MCP server does

You ask your AI something like "open this site and find the price". Your AI uses this helper, which talks to a small extension running inside your browser. The extension then opens tabs, reads the page text, clicks, types, or takes screenshots, and sends the results back. You see the answer or the action right in your chat, and you can watch the browser do it on your screen.

Flow diagram: you ask your AI “Open my browser and find the price of this item”, on your own computer the Chromium Bridge MCP server works with your Chromium browser, and you get back answers and screenshots in chat.

Click to zoom

What you can do with it

Open a new tab and go to a web address
Read the visible text of a page and summarize it
Click buttons and links by description or position
Fill in forms, check boxes, and pick options
Take screenshots of a page or a zoomed region
Run small scripts on the page and see the result
Record a GIF of what happens in a tab

Try asking your AI

“Open my browser and go to news.ycombinator.com, then tell me the top 5 story titles”
“Find the search box on this page, type 'wireless headphones', and press Enter”
“Take a screenshot of the current tab and describe what is on it”
“Fill in the contact form with my name and email and submit it”
“Record a GIF of me scrolling through this page”

What it gives back to you

You get answers in plain chat: page titles, lists of tabs, summaries of page text, or the result of a click or a form fill. Screenshots show up right in the chat feed, and you can click them to see them bigger. If you record a GIF, it is saved as a file you can open. For actions like clicking or typing, your AI tells you what it did.

Before you start

What you need

A Chromium-based browser like Arc, Vivaldi, or Brave
The Claude Code app or another MCP-compatible AI tool
Node.js installed on your computer (the helper program runs on it)
The browser extension loaded from this project (the setup steps are in the README)

Good to know

This tool can click, type, and change things in your browser, so only use it on pages you trust and watch what it does.

Install it with your AI

Add Chromium Bridge MCP server to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check Chromium Bridge MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.

Who it's for

Anyone who wants their AI to actually use the browser for them, like researchers, testers, or office workers who do a lot of copy-paste from websites.