← Discover
GitHub · ChromeDevTools/chrome-devtools-mcp↑ +104 today

Browser debugging for AI

Developed for Chrome DevTools, this server enables coding artificial intelligence agents to manage browser-based debugging processes. Working through the Model Context Protocol, this tool allows agents to directly inspect web applications and automate debugging processes.

Updates

  • October 23, 2026: Stars 53,589 → 54,021, latest release chrome-devtools-mcp-v1.12.0 (October 22, 2026).
  • October 15, 2026: Stars 52,641 → 53,589, latest release chrome-devtools-mcp-v1.11.0 (October 15, 2026).
  • September 27, 2026: Stars 51,328 → 52,641, latest release chrome-devtools-mcp-v1.10.1 (September 23, 2026).
  • September 8, 2026: Stars 49,801 → 51,328, latest release chrome-devtools-mcp-v1.9.0 (September 8, 2026).

What you get

  • Control live browser directly
  • Automating performance analytics
  • Review network requests and console errors

Installation

Global with npm
npm install -g chrome-devtools-mcp

If you don't write code

Paste this into your AI agent (Claude Code · Codex · Antigravity)

Connect to my active browser session using the Chrome DevTools MCP server and analyze performance data from my web application. Check network requests, examine console errors, and perform the necessary debugging steps to troubleshoot any issues I'm encountering.

Repository: https://github.com/ChromeDevTools/chrome-devtools-mcp. Follow the official instructions in the README of this repository for setup and execution.

Before starting, check which OS we are on and if the necessary tools (e.g., Python, Node.js, Git, Docker) are installed. Install any missing ones step-by-step according to this system.

Create a new, empty folder to work in. Do not touch any files outside this folder and do not delete anything. Tell me what you are going to do in one sentence before running each command.

Tell me what I should see on the screen at the end of each step. If an error occurs, I will paste the error message to you exactly as it is, and we will fix it together.

Related dictionary terms

Who it is forIt is suitable for software developers who develop browser-based web applications and want to automate their debugging processes with artificial intelligence agents.
LicenseApache-2.0

Links

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-07-03: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. The introductory text was prepared with AI from the repository's own documentation, and this page was machine-translated from the Turkish original · the Turkish version prevails.