aicoolies logo
chrome-devtools-mcp logo
chrome-devtools-mcp logo

chrome-devtools-mcp

Official Chrome DevTools MCP server for coding agents

open sourceupdated Jun 23, 2026

chrome-devtools-mcp is the Chrome DevTools team's official MCP server that lets coding agents control and inspect a live Chrome browser with first-party Chrome DevTools Protocol fidelity. It exposes Network inspection, Performance traces, Lighthouse audits, console output, and structured DOM snapshots as typed MCP tools, so agents can debug real pages and ship reliable web performance investigations without resorting to brittle DOM scraping.

Read our chrome-devtools-mcp review

A detailed review by the aicoolies team — click to read

chrome-devtools-mcp is the official Model Context Protocol server from the Chrome DevTools team that lets coding agents drive and inspect a live Chrome browser. Rather than relying on brittle DOM scraping or screenshot vision, the server exposes the same capabilities a human engineer uses in DevTools — network inspection, performance traces, Lighthouse audits, console access, emulation, and structured snapshots of the page — as typed MCP tools that any MCP-capable agent can call.

Under the hood the server reuses Chrome's CDP (Chrome DevTools Protocol) surface, so agents get first-party fidelity on the data that actually drives the browser. That makes it a strong fit for agentic debugging workflows: an agent can open a page, capture a performance trace, grab failing requests from the Network panel, run a Lighthouse audit, and explain the regression in a single loop. It slots into Claude Code, Cursor, Windsurf, Copilot and other MCP-capable clients through MCP configuration rather than application-code changes.

The project is Apache-2.0 licensed and maintained inside the ChromeDevTools org, which raises the floor on stability and API coverage compared to community-built browser MCPs. It is particularly useful for web performance work, E2E debugging, and any workflow where the agent needs structured browser telemetry rather than raw pixels or fragile selectors.

Pricing

Free and open source under Apache-2.0 license. You supply your own Chrome install and MCP-capable client (Claude Code, Cursor, Windsurf, Copilot, etc.) — no paid tier or hosted service.

Platforms

Node.js / TypeScript — runs locally, connects to Chrome via CDP and exposes tools to any MCP client (Claude Code, Cursor, Windsurf, Copilot, Claude Desktop)

Categories

Tags

Use Cases

Related Tools

hyperagent

HyperAgent

Open-source natural-language browser automation framework for AI agents

An AGPL-3.0 TypeScript framework that drives a real browser from natural-language tasks — the self-hostable OSS framework from Hyperbrowser, distinct from the vendor's paid cloud browser product.

freeOpen Source
grafana mcp

Grafana MCP Server

First-party MCP server for querying and managing Grafana

Grafana's official Model Context Protocol server, letting AI assistants search dashboards, query datasources, and manage alerts/incidents on your Grafana instance through a standard MCP interface.

Open Source
MCP Registry parent MCP protocol mark

MCP Registry

Official open catalog of Model Context Protocol servers

The official, community-run registry for discovering and publishing Model Context Protocol (MCP) servers — an open index that MCP clients read to find available servers.

Open Source
KaibanJS logo

KaibanJS

JavaScript framework for building and visualizing multi-agent workflows on a Kanban board

KaibanJS is an MIT-licensed JavaScript framework for defining AI agents, tasks, tools, and teams, then orchestrating their work through a Kanban-inspired runtime and visual board. It can run inside Node.js, React, or Next.js projects, supports custom UIs and headless workflows, and provides real-time task-state visibility for multi-agent applications.

Open SourceTelemetry
Figma Console MCP logo

Figma Console MCP

Turn a Figma design system into a programmable API for AI assistants

Figma Console MCP is open-source design-system infrastructure that exposes Figma to AI assistants through MCP. It supports structured extraction, design creation and editing, debugging, accessibility audits, and bidirectional design-token workflows across local, remote read-only, and paired cloud modes; it is not a generic one-click Figma-to-code exporter.

Open SourceTelemetry
MCP Context Forge logo

MCP Context Forge

IBM-backed ContextForge gateway for federating MCP, A2A, REST, and gRPC APIs

MCP Context Forge is IBM’s Apache-2.0 ContextForge project for operating a gateway, registry, and proxy across MCP servers, A2A agents, REST APIs, and gRPC services. It centralizes discovery, authentication, policy controls, federation, and observability, with deployment paths through PyPI, Docker, and Kubernetes.

Open Source

Comparisons

chrome-devtools-mcp vs Browserbase MCP Server — Local DevTools Control vs Hosted Browser Automation

chrome-devtools-mcp and Browserbase MCP Server both give AI agents a browser, but they optimize for different jobs. chrome-devtools-mcp brings Chrome DevTools power to local debugging, inspection, and performance work. Browserbase MCP Server gives agents managed cloud browser sessions with Stagehand-style natural-language automation and session infrastructure.

chrome-devtools-mcpBrowserbase MCP Server

Requestly vs Chrome DevTools MCP — Human Debug Suite or Agent Browser Bridge

Requestly and Chrome DevTools MCP both live in browser-debugging territory, but they target entirely different drivers. Requestly is a decade-old, BrowserStack-backed suite built for humans — frontend engineers and QA testers who intercept, mock, and replay HTTP collaboratively. Chrome DevTools MCP is a Google-maintained Model Context Protocol server that lets AI agents drive a Chrome instance through the MCP standard.

Requestlychrome-devtools-mcp