Provides tools for interacting with Firebase Realtime Database, enabling operations like getting filtered documents, listing collections, and adding documents to the database.
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., "@Firebase Realtime Database get all users with status 'active' from the users collection"
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.
The inspiration for this project was taken from firebase-mcp. Unlike firebase-mcp, which uses Firestore functionalities, firebase-realtimeDB-mcp uses Firebase Realtime Database functionalities. Firebase Realtime Database MCP enables AI assistants to work directly with Firebase services.
Related MCP server: Firestore MCP Server
Firebase project with service account credentials
Node.js environment
Go to Firebase Console → Project Settings → Service Accounts
Click "Generate new private key"
Save the JSON file securely
SERVICE_ACCOUNT_KEY_PATH: Path to your Firebase service account key JSON
FIREBASE_DATABASE_URL: Firebase realtime database URL
A. Run git clone https://github.com/ytzlax/firebase-realtimeDB-mcp.git in the terminal.
B. cd to the cloned path, and run npm i.
C. Run npm run build.
Add the server configuration to your MCP settings file:
Claude Desktop: ~/Library/Application Support/Claude/claude_desktop_config.json
Augment: ~/Library/Application Support/Code/User/settings.json
Cursor: [project root]/.cursor/mcp.json
Follow the guide https://modelcontextprotocol.io/quickstart/user and add the following configuration:
{
"firebase-realtimeDB-mcp": {
"command": "node",
"args": ["/absolute/path/to/dist/index.js"],
"env": {
"SERVICE_ACCOUNT_KEY_PATH": "/absolute/path/to/serviceAccountKey.json",
"FIREBASE_DATABASE_URL": "your-project-id.firebasestorage.app"
}
}
}Tool | Description | Required Parameters |
| Get documents by filter |
|
| List root collections | None |
| Add Document | json object |
This server cannot be deployed
Backend for AI-built apps: database, auth, files, email, AI, payments, deploy, realtime. 170+ tools.
Connects AI assistants to QCDatabase.AI for everyday construction quality-control work.
Interact with your Google Cloud Firestore resources using natural language commands.
Backend for vibe coders. Connect Butterbase to any MCP-compatible AI coding tool and provision a full backend automatically — database, authentication, file storage, edge functions, and real-time — from a natural language prompt. No SQL, no configuration, no backend knowledge required. Free to start at butterbase.ai.
