Chrome DevTools MCP: Browser Debugging and Performance Analysis for Coding Agents

RepositoryChromeDevTools/chrome-devtools-mcpTool

chrome-devtools-mcp connects AI coding agents to Google Chrome via the Model Context Protocol (MCP). It enables agents to automate browser actions using Puppeteer, inspect network traffic and console errors with source maps, and collect detailed performance traces.

Key points

  1. MCP server and standalone CLI allowing coding agents (such as Claude, Cursor, Copilot, or Antigravity) to inspect and drive live Chrome instances.
  2. Automates browser interactions reliably via Puppeteer, incorporating built-in waiting mechanisms for action completion.
  3. Provides advanced debugging capabilities, including network request inspection, screenshots, and console logs with source-mapped stack traces.
  4. Extracts performance insights from DevTools traces and can enrich lab data with real-user metrics from the Google CrUX API.
  5. Collects usage statistics by default and queries CrUX data unless explicitly opted out via command-line flags.

Why it matters

Coding agents frequently lack visibility into runtime browser behaviour, client-side rendering bottlenecks, or console errors. By exposing DevTools directly through a standardised MCP server, models can identify and resolve frontend defects in real browser environments.

Analysis

Maintained by the ChromeDevTools team at Google and licensed under Apache-2.0, the repository exhibits high maturity with extensive adoption (over 50,000 GitHub stars) and integration into the official Chrome developer documentation. It officially supports standard Google Chrome and Chrome for Testing. Development teams should remain mindful of security and data transmission: agents gain full access to inspect browser memory and data, and telemetry is sent to Google unless explicitly disabled using the provided flags.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Repository:captivus/chrome-agent

    chrome-agent: Direct CDP Control for AI Coding Agents

    chrome-agent is a CLI tool and Python library giving AI coding agents direct browser inspection and interaction via the Chrome DevTools Protocol (CDP). It avoids restrictive abstraction layers and enables concurrent, isolated use by multiple agents and human operators.

    243starsPython

    AI & LLMs· Tool

  • Repository:FeiZhuLulu/Agent-Bridge

    Agent Bridge: Orchestrating Local Coding Agents via MCP

    Agent Bridge is an open-source Python tool connecting local coding agents using the Model Context Protocol (MCP). It allows users to interact with a single coordinator agent that delegates tasks to multiple specialized CLI worker agents.

    31starsPython

    AI & LLMs· Tool

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.