Chrome MCP Bridge
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 Hacker News and show me the top 5 article titles"
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
Connecte des assistants IA (Claude, etc.) à votre navigateur Chrome via le Model Context Protocol (MCP).
Architecture
Claude Desktop / AI Client
│
│ MCP Protocol (stdio)
▼
[MCP Server (Node.js)]
│
│ WebSocket (ws://localhost:PORT)
▼
[Chrome Extension]
│
│ Chrome APIs
▼
[Browser]Related MCP server: MCP Chrome Bridge
Outils disponibles
Outil | Description |
| Navigue vers une URL |
| Capture la page active |
| Clique sur un sélecteur CSS |
| Remplit un champ de formulaire |
| Récupère le HTML/texte de la page |
| Liste tous les onglets ouverts |
Installation
1. Serveur MCP
npx chrome-mcp-bridgeOu installation globale :
npm install -g chrome-mcp-bridge
chrome-mcp-bridge2. Extension Chrome
Ouvrez
chrome://extensionsActivez le Mode développeur
Cliquez sur Charger l'extension non empaquetée
Sélectionnez le dossier
extension/dist
3. Configuration Claude Desktop
Ajoutez dans claude_desktop_config.json :
{
"mcpServers": {
"chrome-bridge": {
"command": "npx",
"args": ["chrome-mcp-bridge"],
"env": {
"WS_PORT": "9009"
}
}
}
}Développement
# Installer les dépendances
npm install
# MCP Server
cd mcp-server && npm run dev
# Extension
cd extension && npm run devRelated MCP Connectors
Live browser debugging for AI assistants — DOM, console, network via MCP.
Hosted real Google Chrome MCP with per-user persistent state. Navigate, click, type, screenshot.
Hyperbrowser MCP — wraps the Hyperbrowser AI-agent browsing API
Browser MCP for logged-in tasks. Uses your Chrome — credentials stay local. Zero-token replay.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to control the Google Chrome browser through a Node.js WebSocket bridge and a dedicated browser extension. It provides tools for capturing screenshots, executing JavaScript, managing tabs, and extracting page content via the MCP protocol.2-
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to control Chrome browser actions like navigation, clicking, form filling, screenshots, and console/network logging via an MCP server and Chrome extension.532 npmMIT
- AlicenseBqualityAmaintenanceEnables controlling a real Chrome browser from MCP hosts like Claude, with extension-based or CDP fallback, supporting tabs, navigation, interaction, and page reading tools.401,043 npm6MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI assistants to control your webpage via MCP, allowing navigation, screenshots, clicks, content reading, and more through a Chrome extension.21MIT