home / mcp / firebase realtime database api mcp server

Firebase Realtime Database API MCP Server

MCP Server generated by mcp.ag2.ai

Installation

Add the following to your MCP client configuration file.

Configuration

{
  "mcpServers": {
    "ag2-mcp-servers-firebase-realtime-database-api": {
      "command": "python",
      "args": [
        "mcp_server/main.py",
        "stdio"
      ],
      "env": {
        "CONFIG": "{\"transport\":\"stdio\"}",
        "SECURITY": "KEY=YOUR_API_KEY",
        "CONFIG_PATH": "/path/to/mcp_config.json"
      }
    }
  }
}

You deploy an MCP server that exposes the Firebase Realtime Database API through the Model Context Protocol, enabling you to connect MCP clients to the Firebase REST-style surface with controlled, local or remote transport. This guide walks you through installing, configuring, and running the server for practical development and integration workflows.

How to use

Start the MCP server in stdio mode to run it as a local process that communicates through standard input and output. You will configure the server, then start it and connect your MCP client to the server via the provided stdio channels. The server loads its configuration from the path you provide and uses environment variables for security and runtime control.

How to install

Prerequisites: Python 3.9 or newer, and a working Python environment with pip. You may also use uv for running the server through a lightweight HTTP interface if you prefer. Follow the concrete steps below to set up and start the server.

# 1. Clone the MCP server repository
git clone <repository-url>
cd mcp-server

# 2. Install development dependencies (editable install)
pip install -e ".[dev]"

# Optional: use uv to install and run dependencies
uv pip install --editable ".[dev]"

Running the server

To start the MCP server in stdio mode, run the following command. The server will listen for MCP interactions on its standard IO streams.

python mcp_server/main.py stdio

Configuration and environment

You can customize the server at runtime using environment variables. The following variables control configuration loading and security:

CONFIG_PATH: Path to a JSON configuration file (for example, mcp_server/mcp_config.json).
CONFIG: A JSON string containing the configuration.
SECURITY: Environment variables for security parameters (for example, API keys).

Available tools

start

Launch the MCP server in the specified transport mode (stdio) and load configuration from environment or files. The command accepts the mode as an argument and begins listening for MCP protocol messages on the chosen transport.