Chrome MCP Bridge
Provides AI-driven browser automation for Google Chrome, enabling navigation, form filling, screenshots, and more with real Chrome profiles and sessions.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Chrome MCP BridgeOpen a new tab, go to wikipedia.org, and read the summary."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Chrome MCP Bridge
Part of a 24/7 fully-automated unmanned software development system. This is a standalone component; the core system is proprietary.
AI-driven browser automation for real Chrome — with cookies, login sessions, and extensions intact.
This stdio MCP server lets Claude Code (claude --print) control a visible Chrome browser through the Chrome DevTools Protocol. Unlike headless automation, everything happens in a real browser window — government reviewers can watch every action live.
What It Does
An AI agent can:
Navigate to any URL (government portals, internal systems)
Read page content and accessibility trees
Fill forms automatically (text fields, dropdowns, radio buttons)
Click buttons and submit forms
Take screenshots at every step for audit trails
Execute JavaScript for advanced interactions
All operations use the user's real Chrome profile — existing logins, cookies, and sessions are preserved.
Related MCP server: Chrome MCP Server
Requirements
Requirement | Version |
Python | 3.10+ |
Google Chrome | macOS |
pip packages |
|
Quick Start (Clean Machine)
# 1. Clone and install
cd chrome-mcp-bridge
bash setup.sh
# 2. Launch Chrome with debugging
./launch_chrome.sh
# 3. Run the demo
python3 scripts/demo.pyScreenshots are saved to demo_output/.
Usage with Claude Code
Option A: One-shot command
claude --print --mcp-config mcp-config.json \
"Navigate to google.com and take a screenshot"Option B: Add to any project
Copy the generated mcp-config.json into your project as .mcp.json, or add the server block manually:
{
"mcpServers": {
"chrome": {
"command": "python3",
"args": ["/absolute/path/to/src/chrome_mcp_server.py"],
"env": { "CHROME_CDP_PORT": "9222" }
}
}
}setup.sh generates mcp-config.json with the correct absolute path automatically.
Available Tools
Tool | Description |
| Navigate to a URL |
| Capture JPEG screenshot |
| Click at |
| Type keyboard text |
| Press key combo (e.g. |
| Scroll at position |
| Hover mouse |
| Drag from |
| Find elements by natural language description |
| Fill form field (CSS selector or |
| Read accessibility tree ( |
| Extract visible page text |
| Execute JS in active tab |
| Read browser console logs |
| List open tabs |
| Open new tab |
| Close tab |
| Switch to tab |
| Upload files to file input |
| Wait N seconds |
Architecture
claude --print / Claude Code
| stdio (MCP JSON-RPC)
v
chrome_mcp_server.py
|
+-- Primary: chrome-native-host socket (Claude extension)
+-- Fallback: Chrome DevTools Protocol (CDP) via websocket
|
v
Google Chrome (--remote-debugging-port=9222)The server auto-detects which backend is available. CDP mode works without the Claude extension.
Demo Script
scripts/demo.py runs an end-to-end demonstration:
Navigates to a form page (httpbin.org)
Screenshots the empty form
Finds and fills all form fields automatically
Screenshots the filled form
Submits the form
Screenshots and reads the result
# Chrome must be running with debugging first
./launch_chrome.sh
python3 scripts/demo.pyOutput screenshots are saved to demo_output/ for review.
Troubleshooting
"Could not connect to Chrome"
Ensure Chrome is running with
--remote-debugging-port=9222Verify:
curl http://localhost:9222/json/version
Chrome won't start (port in use)
Another Chrome instance may hold the port. Close it or use a different port:
./launch_chrome.sh 9333
Profile/cookies not loading
If Chrome is already running normally, it locks the profile. Close Chrome first, then launch via the script.
setup.sh fails on pip install
Ensure
pip3is available:python3 -m ensurepip --upgradeOr use a virtual environment:
python3 -m venv .venv && source .venv/bin/activate && bash setup.sh
This server cannot be deployed
Maintenance
Related MCP Connectors
Undetectable cloud browser sessions for AI agents and scrapers. Navigate, extract, click, captcha.
AI-powered browser automation — navigate, click, fill forms, and extract data from any website.
- openhelmOAuthai.openhelm
Autonomous cloud agent tasks: real browser + your tools, structured evidence-backed results.
Stealth web automation for AI agents. Login, signup, navigate, screenshot.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceTransforms Chrome browser into an AI-controlled automation tool that allows AI assistants like Claude to access browser functionality, enabling complex automation, content analysis, and semantic search while preserving your existing browser environment.MIT
- AlicenseNot gradedqualityDmaintenanceA browser extension that turns Chrome into an AI-controlled automation tool, allowing AI assistants like Claude to control your browser, leverage existing login states, and perform complex tasks through a Model Context Protocol server.1MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI coding assistants to control and inspect a live Chrome browser for automation, debugging, performance analysis, network monitoring, and DOM interaction through Chrome DevTools Protocol.1,516,489 npmApache 2.0
- AlicenseNot gradedqualityDmaintenanceEnables AI coding assistants to control and inspect a live Chrome browser through Chrome DevTools for automation, debugging, and performance analysis.1,516,489 npmApache 2.0