ChromeDevTools/chrome-devtools-mcp

Chrome DevTools for coding agents

What it solves

This project provides a way for AI coding agents to interact with and control a live Chrome browser. It bridges the gap between an AI's ability to write code and its ability to observe and debug the actual runtime behavior of a web application in real-time.

How it works

It operates as a Model-Context-Protocol (MCP) server. When connected to an MCP-compatible AI client (like Claude, Cursor, or Copilot), it exposes a set of tools that the AI can call to perform browser actions. It uses Puppeteer for reliable automation and leverages the Chrome DevTools Protocol to access deep browser internals for debugging and performance analysis.

Who it’s for

Web developers and AI-assisted coding agents who need to automate browser interactions, perform in-depth debugging, and analyze web performance directly through an AI interface.

Highlights

  • Browser Automation: Full suite of input and navigation tools (clicking, typing, filling forms, navigating pages).
  • Detailed Debugging: Ability to analyze network requests, take screenshots, and read browser console messages with source-mapped stack traces.
  • Performance Insights: Tools to record traces and extract actionable performance data.
  • Wide Client Support: Ready-made configurations for a vast array of AI IDEs and CLI tools (e.g., Claude Code, Cursor, VS Code, Gemini).
  • Flexible Modes: Includes a --slim mode for basic browser tasks.

Related

  • Project
    AgentDeskAI/browser-tools-mcp

    An MCP server and Chrome extension that gives AI agents access to a user's active browser session for real-time debugging, network inspection, and Lighthouse audits.

  • Project
    obra/superpowers-chrome

    A browser control plugin for AI agents that enables direct Chrome navigation and interaction via the Chrome DevTools Protocol, available as a CLI tool or an MCP server.

  • Project
    mozilla/firefox-devtools-mcp

    An MCP server that enables AI agents to automate and control the Firefox browser via WebDriver BiDi, allowing for web navigation, debugging, and interaction.

  • Project
    vibheksoni/stealth-browser-mcp

    An MCP server that enables AI agents to automate real Chrome-family browsers to bypass anti-bot checks and Cloudflare challenges.

  • Project
    microsoft/DebugMCP

    An MCP server that grants AI coding agents autonomous control over the VS Code debugger to set breakpoints, step through code, and inspect variables locally.