home / mcp / firebase management api mcp server

Firebase Management 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-management-api": {
      "command": "python",
      "args": [
        "mcp_server/main.py",
        "stdio"
      ],
      "env": {
        "CONFIG": "{\"…\":\"...\"}",
        "SECURITY": "YOUR_SECURITY_CONFIG",
        "CONFIG_PATH": "mcp_server/mcp_config.json"
      }
    }
  }
}

You run an MCP server that exposes the Google Firebase API definitions through the MCP protocol, allowing clients to interact with the API in a structured, client-friendly way. This server is built to load the Firebase v1beta1 OpenAPI spec and serve it via MCP transport modes.

How to use

To use the Firebase MCP server, launch it in stdio mode and connect your MCP client to the local process. The server reads its configuration from environment variables or a configuration file, and you can provide security parameters as needed. Once running, your MCP client can request model contexts and actions defined in the Firebase API through the MCP interface without talking raw JSON-RPC.

How to install

Prerequisites are Python 3.9+ and the Python package tools you use for development.

# Step 1: Acquire the code
# Replace <repository-url> with the actual repository URL and run these commands to obtain the MCP server project
# Note: Run these commands in a clean directory where you want the project

git clone <repository-url>
cd mcp_server

# Step 2: Install dependencies (dev environment)
# Use the development setup script if you have a dev container, otherwise install manually
pip install -e ".[dev]"

# Alternative if you prefer uvx tooling
uv pip install --editable ".[dev]"

Running the server

Start the MCP server in stdio mode. This runs the server as a local process that your MCP client can interact with directly.

python mcp_server/main.py stdio

Configuration and security

The server can be configured using environment variables. Provide a path to a JSON configuration file, or supply the configuration directly as a JSON string. You can also define security-related parameters via environment variables to control access to the MCP server.

Environment variables you may use include:

- 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).

Running tests and quality checks

The project uses linting, static analysis, and tests to ensure quality. You can run these locally to verify your setup.

# Linting and formatting
ruff check
ruff format

# Static analysis
./scripts/static-analysis.sh

# Tests and coverage
./scripts/test.sh
./scripts/test-cov.sh

Building and publishing

If you need to build or publish the project, the project uses Hatch for these tasks.

hatch build
hatch publish

Available tools

linting

ruff is used to check for linting issues and format code to a consistent style.

formatting

ruff format reformats code to the project's formatting standards.

static analysis

mypy, bandit, and semgrep are run to verify types and scan for security concerns.

testing

pytest runs to execute tests and generate coverage reports.

pre-commit

pre-commit hooks run automatically before commits to catch issues early.