Chrome DevTools MCP

Name: Chrome DevTools MCP
Author: Google Chrome Team

Control and inspect a live Chrome browser from AI agents

Official

Developer Tools

Install Command

npx @chrome-devtools/mcp-server

Claude Desktop Config

{
  "mcpServers": {
    "chrome-devtools": {
      "command": "npx",
      "args": ["-y", "@chrome-devtools/mcp-server"]
    }
  }
}

Chrome DevTools MCP is an officially maintained MCP server in the Developer Tools category, developed by Google Chrome Team. It runs locally on your machine, keeping your data private and giving you full control over the connection. Developers can use it to bring AI assistance directly into their build and coding environment.

About Chrome DevTools MCP

The official Chrome DevTools MCP server from Google lets AI coding agents control and inspect a live Chrome browser session.

Features

Full Chrome DevTools Protocol access
DOM inspection and manipulation
JavaScript execution in browser context
Network request monitoring
Performance profiling
Console log access

Who Should Use Chrome DevTools MCP?

1Control a browser and scrape the web through Claude
2Speed up coding workflows by letting Claude interact with your dev environment
3Run terminal commands, manage processes, and inspect logs via AI
4Integrate AI assistance directly into your build and CI pipelines

How to Install Chrome DevTools MCP

Before you start

You will need Node.js (v18 or later) installed on your machine — download it from nodejs.org if you haven't already.

1Open a terminal (Terminal on Mac, Command Prompt or PowerShell on Windows).
2Paste the install command above and press Enter — Node.js will download and run the server automatically.
3Add the server to your Claude Desktop config file (see the JSON snippet above) and restart Claude.

The Claude Desktop config snippet above can be copied and pasted directly into your claude_desktop_config.json file — no editing required.

How Chrome DevTools MCP Compares

✦It is an officially maintained server — unlike community alternatives, it is built and supported by the original project team, ensuring compatibility with upstream changes.

✦It runs entirely on your local machine, so no data leaves your environment — important for teams with privacy or compliance requirements.