Practical overview
When it fits
Use it when an AI coding workflow needs live Chrome interaction, DevTools-based debugging, repeatable browser automation or performance investigation.
Who it is for
- Developers using MCP-compatible coding agents
- Teams building browser automation or browser subagents
- Developers investigating Chrome console, network or performance behavior
Documented uses
- Control a live Chrome browser from a coding agent
- Automate browser actions with reliable waits
- Inspect network requests, screenshots and console messages
- Record traces and extract performance insights
- Use Chrome DevTools capabilities without MCP through the provided CLI
Requirements & limits
The repository is public and licensed under Apache-2.0. Documented setup requires Node.js LTS, npm and current stable Chrome or newer. Usage statistics are enabled by default, with a documented opt-out flag.
- Choose the MCP integration when the browser should be controlled by a compatible coding agent.
- Choose the CLI when Chrome DevTools functionality is needed without MCP.
- Use slim mode for the documented basic-browser-task configuration.
- Use caution with browser data because MCP clients can inspect, debug and modify browser or DevTools content.
- Check browser support carefully: Google Chrome and Chrome for Testing are officially supported; other Chromium-based browsers are not guaranteed.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Add Chrome DevTools MCP to an MCP client
Connect an MCP client to the Chrome DevTools MCP server and run the documented first performance check.
Before you start
- Node.js LTS
- npm
- Current stable Google Chrome or newer
- An MCP client
Steps
Add the documented mcpServers configuration using npx and chrome-devtools-mcp@latest.
Start or connect the MCP client with that configuration.
Enter the first-prompt example: Check the performance of https://developers.chrome.com.
Allow the server to start the browser when the performance tool is used and record a trace.
Expected outcome
The MCP client should open Chrome and record a performance trace for the specified page.
Guide limitations
- The project officially supports Google Chrome and Chrome for Testing only; other Chromium-based browsers are not guaranteed.
- The server does not automatically start the browser merely when the MCP client connects.
- The documented agent-specific compatibility requirements are not detailed here.
Compare options for AI coding assistance
These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.
| Project | Documented purpose | Platform | Access and requirements |
|---|---|---|---|
| Chrome Devtools MCP | Control a live Chrome browser from a coding agent | Browser Extension, CLI, Desktop | The repository is public and licensed under Apache-2.0. Documented setup requires Node.js LTS, npm and current stable Chrome or newer. Usage statistics are enabled by default, with a documented opt-out flag. |
| Overture | Inspect a coding agent’s planned steps and branches before code is written. | Self-hosted, Server, Web | Open-source software under the MIT license. The documented setup runs the MCP server locally and opens its web interface at `http://localhost:3031` by default. |
| Wigolo | Search the web and fetch pages for an agent’s research task. | CLI, Self-hosted, Server | The quickstart lists macOS, Linux and Windows, and requires Node.js 20 or later with about 1.5 GB of free disk space. The repository labels the project public beta. |
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 1 October 2026
- Original website title
- ChromeDevTools/chrome-devtools-mcp · Official homepage title · retained in its source language