What browsers are supported?

Chrome DevTools MCP officially supports Google Chrome and Chrome for Testing only. Other Chromium-based browsers may work but are not guaranteed.

What are the requirements?

Node.js v20.19 or newer, Chrome current stable version or newer, and npm.

Slim mode provides a reduced set of tools for basic browser tasks. Use the --slim flag to enable it.

chrome-devtools-mcp exposes the browser instance content to MCP clients. Avoid sharing sensitive or personal information you don't want shared with MCP clients. Usage statistics are collected by default but can be disabled with --no-usage-statistics.

Chrome DevTools MCP

Name: Chrome DevTools MCP
Author: Chrome DevTools Team

by Chrome DevTools Team

officialstdionpmVerified

View all implementations

36.4kstars|2.2kforks

View on GitHub npm Docs

Works withClaude DesktopCursorVS CodeWindsurf

About

Official Chrome DevTools MCP server for AI coding agents — control Chrome, debug pages, analyze performance, and automate browser tasks.

Features

Get performance insights using Chrome DevTools to record traces and extract actionable insights
Advanced browser debugging — analyze network requests, take screenshots, check console messages with source-mapped stack traces
Reliable automation using Puppeteer to automate actions in Chrome and automatically wait for results
Input automation tools: click, fill, drag, hover, type, keyboard shortcuts, file upload
Navigation automation: navigate pages, manage tabs, wait for conditions
Network inspection: list and inspect network requests
JavaScript evaluation in browser context
Lighthouse performance audits
Chrome DevTools performance tracing and analysis
Memory snapshots for leak detection
Device emulation and page resizing
Slim mode for basic browser tasks
CLI for non-MCP usage

Use Cases

Web Developer

Verify code changes in real-time by navigating to pages, taking screenshots, and inspecting console output

QA Engineer

Diagnose network and console errors by listing requests and messages with source-mapped traces

Frontend Developer

Debug live styling and layout issues by taking snapshots and evaluating JavaScript in the browser

Performance Engineer

Automate performance audits with Lighthouse and trace analysis to identify bottlenecks

AI Coding Agent

Simulate user behavior — click buttons, fill forms, navigate flows — to test applications end-to-end

What This Server Can Do

MCP servers expose three types of capabilities to AI clients. Here's what Chrome DevTools MCP supports.

Tools

Supported29 tools

Functions your AI client can call to perform actions — like querying a database, creating a file, or calling an API.

How to use: Tools run automatically when your AI client decides they're needed. Ask your AI assistant to perform a task, and it will invoke the right tool.

Resources

Not available

This server does not expose read-only data resources.

Prompts

Not available

This server does not provide pre-built prompt templates.

For the full list of available tools, resources, and prompts, check the README on GitHub.

Available Tools (29)

click

Click on an element by its uid from the page snapshot

drag

Drag an element onto another element

fill

Type text into an input, textarea, or select an option from a select element

fill_form

Fill out multiple form elements at once

handle_dialog

Handle a browser dialog (accept or dismiss)

hover

Hover over an element by its uid

press_key

Press a key or key combination

type_text

Type text using keyboard into a previously focused input

upload_file

Upload a file through a provided element

close_page

Close the current page

list_pages

List all open pages/tabs

navigate_page

Navigate to a URL

new_page

Open a new page/tab

select_page

Select a page/tab by index

wait_for

Wait for a condition on the page

emulate

Emulate a device

resize_page

Resize the page viewport

performance_analyze_insight

Analyze a performance insight from a trace

performance_start_trace

Start recording a performance trace

performance_stop_trace

Stop recording and analyze the performance trace

get_network_request

Get details of a specific network request

list_network_requests

List all network requests

evaluate_script

Evaluate JavaScript in the browser context

get_console_message

Get details of a specific console message

lighthouse_audit

Run a Lighthouse performance audit

list_console_messages

List all console messages

take_screenshot

Take a screenshot of the current page

take_snapshot

Take an accessibility snapshot of the current page

take_memory_snapshot

Take a heap snapshot for memory leak detection

Alternative Implementations

Other MCP servers for the same service.

View all on service page

Playwright MCP

official95/100

32.0k