Chrome MCP Docker Server

Provides persistent Chrome DevTools access to AI coding assistants via MCP, with stable sessions and host header bypass.

other

GitHub Stars

other

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "null-runner-chrome-mcp-docker": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "--network",
        "host",
        "-e",
        "CHROME_HOST=localhost",
        "-e",
        "CHROME_PORT=9222",
        "nullrunner/chrome-mcp-docker:latest"
      ],
      "env": {
        "CHROME_HOST": "localhost",
        "CHROME_PORT": "9222"
      }
    }
  }
}

You can run a persistent Chrome DevTools MCP Server to power AI coding assistants, giving you reliable session persistence, stable Docker-based hosting, and direct Chrome DevTools Protocol access from your MCP client.

How to use

Use an MCP client (such as Claude Code) to connect to the Chrome MCP Docker server. The server exposes a persistent Chrome instance that your assistant can control through the Chrome DevTools Protocol. You benefit from stable sessions, console logs, mobile mode, host header bypass, and direct interactions with the browser during coding sessions.

Available tools

navigate

Go to a URL and wait for the page to load.

screenshot

Capture the current viewport image from the browser.

click

Click a DOM element within the page.

type

Type text into an input field or editable area.

scroll

Scroll the page or a specific element.

wait_for_selector

Wait for a specific element to appear in the DOM.

get_computed_styles

Inspect computed CSS styles for debugging.

get_network_errors

Detect failed network requests in the page.

get_console_logs

Capture JavaScript console output from the page.

mobile_mode

Switch to a mobile viewport like iPhone X for testing responsive layouts.

Built by

VeilStrat

AI signals for GTM teams