linkgo
Chrome DevTools MCP

Chrome DevTools MCP

AI

Official Chrome DevTools MCP server that lets coding agents drive, inspect and profile a live Chrome browser.

-(0 Reviews)
Free Available
Starting from Free
Visit Official Site

About Chrome DevTools MCP

chrome-devtools-mcp is the official Model Context Protocol server from the Chrome DevTools team. It gives a coding agent such as Claude, Cursor, Copilot or Antigravity direct control over a real Chrome instance, exposing the capabilities normally reached through DevTools. Agents can record performance traces using the DevTools frontend and extract actionable insights, inspect network requests, capture screenshots, and read console messages with source-mapped stack traces. Automation is built on Puppeteer, so actions wait for their results instead of relying on fixed sleeps, which makes multi-step browser tasks far more reliable than screenshot-and-click approaches. A standalone CLI is provided for use outside an MCP client. Because the server exposes browser contents to connected clients, the project documents the trust boundary plainly: any data in the browser or DevTools can be inspected and modified. Google Chrome and Chrome for Testing are the officially supported targets, with fixes committed against the latest Extended Stable release. Performance tooling may query the CrUX API for field data and usage statistics are collected by default, both of which can be disabled with flags.

Key Features

Performance insights: Records traces with the Chrome DevTools frontend and extracts actionable findings
Network inspection: Lets an agent read requests and responses from the live browser session
Console access: Surfaces console messages with source-mapped stack traces for real debugging
Screenshots: Captures the current page state on demand for the agent to reason over
Puppeteer-backed automation: Actions automatically wait for their results rather than using fixed delays
Standalone CLI: Ships a command-line interface for use without an MCP client
Privacy flags: --no-performance-crux and --no-usage-statistics disable external data collection
Broad client support: Works with Claude, Cursor, Copilot, Antigravity and other MCP-capable agents

Use Cases

A coding agent reproduces a reported bug in a live page and reads the console stack trace to locate the cause
A developer asks an agent to record a performance trace and summarise which resources block first paint
An agent verifies a front-end change by navigating the app and confirming the network calls it expects
A QA workflow captures screenshots across a checkout flow without writing a bespoke automation script
An engineer debugs a source-mapped production error by having the agent inspect the deployed page directly
A team wires the CLI into an existing pipeline to collect DevTools traces without adopting an MCP client

Frequently asked questions about Chrome DevTools MCP

What is Chrome DevTools MCP?

Official Chrome DevTools MCP server that lets coding agents drive, inspect and profile a live Chrome browser.

How does Chrome DevTools MCP work?

Chrome DevTools MCP works by combining Performance insights: Records traces with the Chrome DevTools frontend and extracts actionable findings, Network inspection: Lets an agent read requests and responses from the live browser session, Console access: Surfaces console messages with source-mapped stack traces for real debugging, Screenshots: Captures the current page state on demand for the agent to reason over, Puppeteer-backed automation: Actions automatically wait for their results rather than using fixed delays to help users with A coding agent reproduces a reported bug in a live page and reads the console stack trace to locate the cause, A developer asks an agent to record a performance trace and summarise which resources block first paint, An agent verifies a front-end change by navigating the app and confirming the network calls it expects, A QA workflow captures screenshots across a checkout flow without writing a bespoke automation script, An engineer debugs a source-mapped production error by having the agent inspect the deployed page directly.

What are the main features of Chrome DevTools MCP?

Key features include Performance insights: Records traces with the Chrome DevTools frontend and extracts actionable findings, Network inspection: Lets an agent read requests and responses from the live browser session, Console access: Surfaces console messages with source-mapped stack traces for real debugging, Screenshots: Captures the current page state on demand for the agent to reason over, Puppeteer-backed automation: Actions automatically wait for their results rather than using fixed delays.

Who is Chrome DevTools MCP for?

Chrome DevTools MCP is useful for anyone interested in A coding agent reproduces a reported bug in a live page and reads the console stack trace to locate the cause, A developer asks an agent to record a performance trace and summarise which resources block first paint, An agent verifies a front-end change by navigating the app and confirming the network calls it expects, A QA workflow captures screenshots across a checkout flow without writing a bespoke automation script, An engineer debugs a source-mapped production error by having the agent inspect the deployed page directly.

How much does Chrome DevTools MCP cost?

Chrome DevTools MCP is free to use.

How do I get started with Chrome DevTools MCP?

Visit https://github.com/ChromeDevTools/chrome-devtools-mcp to sign up and explore Chrome DevTools MCP.

Explore more AI Mcps tools

Browse all Mcps tools →

Compare Chrome DevTools MCP: vs OzBrain · vs QApilot MCP for Android · vs Noodle Seed · vs TrackMCP