Skip to content

Summary

Google's official MCP server for driving and inspecting a real Chrome browser — automation, debugging, and performance traces.

Features

  • Drive a live Chrome browser: navigate, click, fill forms
  • Read console messages, network requests, and responses
  • Snapshot the DOM and accessibility tree
  • Record performance traces and extract Core Web Vitals
  • Evaluate scripts in the page context
  • Available as a standalone MCP server or a Claude Code plugin

Installation

Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.

Any MCP-compatible agent

Most agents (Claude, Cursor, Windsurf, VS Code, and more) read a standard mcpServers configuration.

  1. Open your agent's MCP configuration file.
  2. Merge the snippet below into it.
  3. Restart the agent — the "Chrome DevTools MCP" tools will be available.
{
  "mcpServers": {
    "chrome-devtools-mcp": {
      "command": "npx",
      "args": [
        "chrome-devtools-mcp@latest"
      ]
    }
  }
}

Description

Chrome DevTools MCP, maintained by the Google Chrome DevTools team, gives coding agents a direct line into a real Chrome browser over the Chrome DevTools Protocol. Instead of writing and maintaining Puppeteer scripts, an agent can drive the browser and read back what actually happened.

It covers three jobs. Automation: navigate, click, fill forms, upload files, and wait on page state. Debugging: read console messages, inspect network requests and responses, take snapshots of the DOM and accessibility tree, and evaluate scripts in the page. Performance: record traces, extract Core Web Vitals, and get concrete insight into what is making a page slow — which is what makes it useful for verifying a fix rather than just guessing at one.

It officially supports Google Chrome and Chrome for Testing, runs locally via npx, and ships both as a standalone MCP server and as a Claude Code plugin that bundles matching skills.

Related MCP Servers

MCP: Engram

by Gentleman Programming

New

Persistent memory for coding agents as a single Go binary — SQLite and FTS5 behind MCP, an HTTP API, a CLI and a TUI, with no Node, Python or Docker required.

MCP: agent-device

by Callstack

New

Give a coding agent a live feedback loop on real mobile, TV and desktop apps — inspect, tap, type and capture evidence on iOS, Android and HarmonyOS over MCP or a CLI.

New

The official W&B MCP server: query experiment runs, Weave LLM traces, artifacts and registries in natural language, and write findings back as a W&B report.

Featured

Replicate's official MCP server: search thousands of hosted models, read their schemas, and run predictions on image, video, audio and language models from inside an agent.

Browse all MCP servers →