MCP Servers · ChromeDevTools

chrome-devtools-mcp

Chrome DevTools MCP is a TypeScript server that lets AI coding agents control and inspect live Chrome browsers via the Model-Context-Protocol. It provides browser automation, debugging, performance tracing, and screenshot capabilities for agents like Claude, Cursor, and Copilot.

Talk to DEV.co Discuss Implementation

Source: GitHub — github.com/ChromeDevTools/chrome-devtools-mcp

46.3k

GitHub stars

Forks

TypeScript

Primary language

Apache-2.0

License (OSI-approved)

Key facts

Objective fields from the source. Values we can't verify are shown as “Unknown” rather than guessed.

Field	Value
Repository	ChromeDevTools/chrome-devtools-mcp
Owner	ChromeDevTools
Primary language	TypeScript
License	Apache-2.0 — OSI-approved
Stars	46.3k
Forks	3k
Open issues	96
Latest release	chrome-devtools-mcp-v1.5.0 (2026-07-03)
Last updated	2026-07-08
Source	https://github.com/ChromeDevTools/chrome-devtools-mcp

What chrome-devtools-mcp is

Built as an MCP server, it wraps Chrome DevTools and Puppeteer to expose browser automation and introspection capabilities to LLM agents. Supports performance tracing with CrUX integration, network inspection, console logging with source maps, and headless or headed browser modes.

Quickstart

Get the chrome-devtools-mcp source

Clone the repository and explore it locally.

terminalbash

1git clone https://github.com/ChromeDevTools/chrome-devtools-mcp.git2cd chrome-devtools-mcp3# follow the project's README for install & configuration

Need it deployed, integrated, or customized instead? DEV.co ships production installs.

Best use cases

AI Agent Web Automation

Enable coding agents to perform reliable browser interactions (navigation, form filling, clicking) with automatic wait logic and action verification via DevTools.

Performance Analysis & Optimization

Collect DevTools traces and performance metrics (with real-user CrUX data) to identify bottlenecks and provide actionable performance recommendations to agents.

Intelligent Debugging & QA

Agents can capture screenshots, inspect network requests, analyze console errors with source-mapped stack traces, and debug live web applications interactively.

Implementation considerations

Requires Node.js LTS, Chrome (current stable or newer), and npm; agents must have access to a Chrome binary or browser instance.
Telemetry and update checks are enabled by default—review privacy requirements and disable via flags or env vars before production deployment.
CrUX integration sends performance trace data to Google APIs; disable with `--no-performance-crux` flag if data residency is a concern.
MCP client integration varies by platform (Copilot, Claude, Cline, Antigravity, etc.); refer to client-specific configuration docs in the README.
Slim mode (`--slim --headless`) available for basic tasks if full DevTools overhead is not needed.

When to avoid it — and what to weigh

Sensitive Data in Browser — The README explicitly warns that MCP clients can inspect and modify all browser content; do not use with personal or sensitive information you don't want to share with agents.
Non-Chrome/Chromium Browsers — Officially supports only Google Chrome and Chrome for Testing. Chromium-based alternatives may work but are unsupported and may exhibit unexpected behavior.
Privacy-Critical Deployments — Telemetry is enabled by default (tool invocation metrics, latency, environment data sent to Google). Opt-out requires flags; CI environments auto-disable but production use requires explicit configuration.
Offline or Air-Gapped Environments — Performs periodic update checks and may call Google CrUX API for performance data; requires network access and external service dependencies.

License & commercial use

Apache License 2.0 (Apache-2.0). Permissive OSI-approved license allowing commercial use, modification, and distribution, provided notice and changes are documented and license is included.

Apache-2.0 is a permissive OSI license; commercial use is permitted. However, this project is maintained by Google (evident from privacy policy references and CrUX integration), and data collection is enabled by default. Review Google's terms for telemetry and CrUX integration in your commercial deployment; validate compliance with your legal/privacy teams.

DEV.co evaluation signals

Editorial assessment — not user reviews. Directional, with an explicit confidence level.

Signal	Assessment
Maintenance	Active
Documentation	Strong
License clarity	Clear
Deployment complexity	Moderate
DEV.co fit	Strong
Assessment confidence	High

Security considerations

No explicit security audit or vulnerability disclosure policy mentioned. Key points: (1) MCP exposes all browser content to clients—ensure agents and users are trusted. (2) Telemetry is enabled by default; Google collects tool metrics and environment data. (3) CrUX API calls send trace data to Google; disable if data residency is critical. (4) Requires Chrome binary execution; run with appropriate OS-level sandboxing. (5) No mention of SBOM, CVE tracking, or dependency security scanning in README.

Alternatives to consider

Playwright MCP / Puppeteer directly

Both provide browser automation but lack integrated DevTools introspection, performance tracing, and CrUX alignment; requires custom orchestration for agents.

Selenium + custom MCP wrapper

More mature/multi-browser but heavier, lacks DevTools ecosystem integration, and requires additional wrapper code to expose as MCP server.

Custom browser extension + MCP bridge

Offers fine-grained control but requires extension development, maintenance, and is not suitable for automated agent-driven workflows at scale.

Software development agency

Build on chrome-devtools-mcp with DEV.co software developers

Add browser automation and debugging capabilities to your coding agents. Review the README for MCP client setup, telemetry options, and security considerations before deployment.

Talk to DEV.co

Related open-source tools

Surfaced by semantic similarity across the DEV.co open-source index.

browser-tools-mcp mcp stealth-browser-mcp

Related on DEV.co

Explore the category and the services that help you build with it.

MCP Servers AI Application Development Web App Development DevOps Talk to DEV.co

chrome-devtools-mcp FAQ

Is Chrome DevTools MCP secure for production use?

No explicit security audit is documented. Ensure agents/users are trusted, review telemetry and CrUX integration settings, run Chrome with OS-level sandboxing, and disable data collection flags if required by policy.

Can I use Chromium or Edge instead of Chrome?

The README states that only Google Chrome and Chrome for Testing are officially supported. Other Chromium-based browsers may work but are unsupported and behavior is not guaranteed.

How do I disable telemetry and update checks?

Use `--no-usage-statistics` and `--no-update-checks` flags, or set env vars `CHROME_DEVTOOLS_MCP_NO_USAGE_STATISTICS`, `CHROME_DEVTOOLS_MCP_NO_UPDATE_CHECKS`, or `CI`. Telemetry is auto-disabled in CI environments.

What MCP clients are supported?

Tested with Copilot, Claude Code, Cline, Antigravity, Codex, Command Code, Amp, and Copilot CLI. Each has specific configuration instructions in the README; compatibility with other MCP clients is not documented.

Work with a software development agency

Adopting chrome-devtools-mcp is usually one piece of a larger software development effort. As a software development agency, DEV.co provides software development services and web development expertise — pairing senior software developers and web developers with your team to design, build, and operate mcp servers software in production.

Integrate Chrome DevTools into Your AI Agent Workflow

Add browser automation and debugging capabilities to your coding agents. Review the README for MCP client setup, telemetry options, and security considerations before deployment.

Talk to DEV.co Schedule a Consultation