Google Launches Public Preview of Chrome DevTools MCP Server for AI Coding Assistants
The Chrome DevTools MCP server is available for setup via npm, with detailed documentation accessible on GitHub.
September 24, 2025 — Google has announced the public preview of the Chrome DevTools Model Context Protocol (MCP) server, a new tool designed to enhance the capabilities of AI coding assistants by integrating Chrome’s debugging and performance analysis directly into their workflows.
According to Google, AI agents often face a major limitation: they cannot see how the code they generate actually behaves in a live browser. "The Chrome DevTools MCP server changes this. AI coding assistants are able to debug web pages directly in Chrome, and benefit from DevTools debugging capabilities and performance insights. This improves their accuracy when identifying and fixing issues," Google employees Mathias Bynens & Michael Hablich wrote in a blog post.
Announcing our public preview of Chrome DevTools MCP! Experience the full power of DevTools in your AI coding agent → https://t.co/u5kOrjFgrq
— Chrome for Developers (@ChromiumDev) September 23, 2025
With Chrome DevTools MCP, your AI agent can run performance traces, inspect the DOM, & perform real-time debugging of your web pages. pic.twitter.com/aKgmArbihX
The Model Context Protocol (MCP) is an open-source standard that connects large language models (LLMs) to external tools and data sources. By adopting MCP, the DevTools server gives AI agents access to features such as performance_start_trace, allowing them to launch Chrome, run performance tests, and analyze results to recommend optimizations.
Developers can now instruct AI assistants to verify code changes in the browser, diagnose network and console errors, simulate user interactions, debug layout and styling problems, and even run automated performance audits.
The Chrome DevTools MCP server is available for setup via npm, with detailed documentation accessible on GitHub.
Comments ()