Happy slice of mcp pizzaMCP.pizza

mcp-chrome

MCP.Pizza Chef: hangwin

With this tool installed as a Chrome extension, your assistant can open tabs, click buttons, fill out forms, take screenshots, and read your bookmarks and browsing history β€” all inside the same Chrome window you already use, logins and settings included. It can also search across everything open in your browser by meaning rather than exact wording, so you can find a tab even if you don't remember what it said. It works with any assistant that supports MCP, including Claude Desktop, and needs Node.js installed on your computer plus a one-time browser extension setup. No account or paid API key required.

Data
Web/Research

Use This MCP server To

Fill out and submit a web form for me Take a screenshot of the page I'm viewing Search all my open tabs by meaning, not exact words Look up something from my browsing history or bookmarks Click through a multi-step task on a website for me Pull the text or details off a webpage I'm on Check what a page is loading or talking to in the background

README

Chrome MCP Server πŸš€

Stars License: MIT TypeScript Chrome Extension Release

🌟 Turn your Chrome browser into your intelligent assistant - Let AI take control of your browser, transforming it into a powerful AI-controlled automation tool.

πŸ“– Documentation: English | δΈ­ζ–‡

The project is still in its early stages and is under intensive development. More features, stability improvements, and other enhancements will follow.

🎯 What is Chrome MCP Server?

Chrome MCP Server is a Chrome extension-based Model Context Protocol (MCP) server that exposes your Chrome browser functionality to AI assistants like Claude, enabling complex browser automation, content analysis, and semantic search. Unlike traditional browser automation tools (like Playwright), Chrome MCP Server directly uses your daily Chrome browser, leveraging existing user habits, configurations, and login states, allowing various large models or chatbots to take control of your browser and truly become your everyday assistant.

✨ New Features(2025/12/30)

  • A New Visual Editor for Claude Code & Codex, for more detail here: VisualEditor

✨ Core Features

mcp-chrome FAQ

Can I use this to fill out and submit online forms automatically?
Yes β€” once it's set up, you can ask your assistant to find a form on the page you're viewing, fill in the fields, and submit it for you.
Can I use this to search through many open browser tabs at once?
Yes β€” it can look across everything you have open and find the tab that matches what you're thinking of, even if you don't remember the exact words on the page.
Do I need to create an account or get a paid API key to use this?
No account or paid API key is required. You do need Node.js installed on your computer and a Chrome extension you load once during setup.
Which AI assistants or apps can I use this with?
It works with any assistant or app that supports MCP, including Claude Desktop and other similar assistants β€” you're not locked into one company's tool.
Will it use my existing logins and saved browser settings?
Yes β€” because it runs inside your own Chrome browser, it automatically uses whatever you're already logged into instead of opening a fresh browser and asking you to sign in again.
Is my browsing data sent anywhere?
No β€” everything runs locally on your own computer, so your browsing stays private to your machine.
How hard is it to set up?
You'll install a Chrome extension and a small helper program on your computer, which takes a little technical comfort but no coding.
Can it take screenshots of what I'm looking at?
Yes β€” you can ask your assistant to capture the current page or a specific part of it.