GitHub's official MCP server that lets AI assistants read repositories, manage issues and pull requests, and work with GitHub Actions.
ChromeDevTools/chrome-devtools-mcp
An MCP server that lets coding agents control and inspect a live Chrome browser using Chrome DevTools for debugging and performance analysis.
- Stars
- 53,868
- Forks
- 7,035
- Open issues
- 152
- Last commit
- 11 hours ago
What is it?
Chrome DevTools for agents (chrome-devtools-mcp) is a Model Context Protocol server that gives AI coding assistants such as Claude, Cursor, Copilot and Antigravity access to a running Chrome browser. Through it, an agent can drive pages, take screenshots, read network requests and console messages with source-mapped stack traces, and record performance traces.
The server is built on Chrome DevTools and uses Puppeteer to automate actions and wait for their results. The browser starts automatically when a client calls a tool that needs one. A CLI is also provided for use without MCP, and a slim mode exposes a smaller set of basic browser tools, optionally headless.
The project officially supports Google Chrome and Chrome for Testing. Because the server exposes browser content to the connected client, it can read and modify any data in the browser, so sensitive pages should be avoided. Usage statistics collection is on by default and can be disabled with a flag or environment variable.
Key features
- 01Records performance traces and extracts actionable insights using Chrome DevTools.
- 02Inspects network requests, takes screenshots and reads console messages with source-mapped stack traces.
- 03Automates browser actions with Puppeteer and waits for results automatically.
- 04Offers a slim mode with basic tools and a headless option.
- 05Provides a CLI for use without MCP.
Use cases
- Letting an AI coding assistant debug a web page's console errors and network failures.
- Running performance audits on a site and getting trace-based recommendations.
- Automating browser tests driven by an agent during development.
- Embedding a browser subagent in agentic tooling.
Quick start
- 1
Install Node.js LTS and Chrome (current stable)
- 2
Add the MCP server config to your MCP client
npx -y chrome-devtools-mcp@latest - 3
Enter the test prompt in your MCP client to check it works
Things to know
- Officially supports only Google Chrome and Chrome for Testing; other Chromium browsers are not guaranteed.
- Tools can expose all browser data to the MCP client, so avoid sharing sensitive information.
- Usage statistics collection is enabled by default and must be opted out of with a flag or environment variable.
Topics
FAQ
- What is chrome-devtools-mcp?
- An MCP server that lets coding agents control and inspect a live Chrome browser using Chrome DevTools for debugging and performance analysis. Chrome DevTools for agents (chrome-devtools-mcp) is a Model Context Protocol server that gives AI coding assistants such as Claude, Cursor, Copilot and Antigravity access to a running Chrome browser. Through it, an agent can drive pages, take screenshots, read network requests and console messages with source-mapped stack traces, and record performance traces.
- Is chrome-devtools-mcp free to use? What license does it have?
- chrome-devtools-mcp is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
- Is chrome-devtools-mcp still maintained?
- Actively maintained. The last commit to chrome-devtools-mcp was on Oct 19, 2026.
- What can I use chrome-devtools-mcp for?
- Letting an AI coding assistant debug a web page's console errors and network failures. Running performance audits on a site and getting trace-based recommendations. Automating browser tests driven by an agent during development. Embedding a browser subagent in agentic tooling.
- How do I install chrome-devtools-mcp?
- Install Node.js LTS and Chrome (current stable) Add the MCP server config to your MCP client: npx -y chrome-devtools-mcp@latest Enter the test prompt in your MCP client to check it works
- Where can I get chrome-devtools-mcp?
- The source code and installation instructions are on GitHub: https://github.com/ChromeDevTools/chrome-devtools-mcp
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
An MCP server with a native C++ Unreal Editor plugin that lets AI assistants build levels, Blueprints, materials and more inside a running editor.
An Electron-based, local-first browser where AI agents operate inside your real logged-in browser session via MCP or HTTP API.
Cherry Studio is a cross-platform desktop AI client that connects to many LLM providers, local models and 300+ preset assistants.
A terminal coding agent with built-in LSP, debugger, browser and subagent tools, supporting 60+ model providers.
Blender add-on and MCP server that let AI assistants like Claude build, modify and inspect 3D scenes in Blender through prompts.