home / mcp / cloud sql admin mcp server

Cloud SQL Admin MCP Server

MCP Server generated by mcp.ag2.ai

Installation

Add the following to your MCP client configuration file.

Configuration

{
  "mcpServers": {
    "ag2-mcp-servers-cloud-sql-admin-api": {
      "command": "python",
      "args": [
        "mcp_server/main.py",
        "stdio"
      ],
      "env": {
        "CONFIG": "{\"name\":\"value\"}",
        "SECURITY": "API_KEY=YOUR_API_KEY",
        "CONFIG_PATH": "mcp_server/mcp_config.json"
      }
    }
  }
}

You can run an MCP server that exposes the Google Cloud SQL Admin API specification through a consistent model-context protocol. This server lets MCP clients discover, explore, and interact with the API in a standardized way, enabling tooling and automation across different environments.

How to use

Start the local MCP server in stdio mode and connect an MCP client to it. You will use the standard stdio transport to exchange messages with the server on your local machine or within a development container. The server reads its configuration from environment variables or a JSON config file you provide, and it exposes the API model via the MCP interface so clients can fetch type definitions, endpoints, and actions for the Google Cloud SQL Admin API.

How to install

Prerequisites go on your machine. You need Python 3.9 or newer, and you should have pip and uv installed.

Step 1: Clone the project repository and enter the directory.

git clone <repository-url>
cd mcp_server

Step 2: Install development dependencies. Use the editable install for the project’s dev extras.

pip install -e ".[dev]"

If you prefer using uv for running Python dependencies, you can also install with uv as shown.

uv pip install --editable ".[dev]"

Step 3: Run the MCP server in stdio mode. This starts the server using the exact command shown in the source.

python mcp_server/main.py stdio

Step 4: Configure runtime parameters. You can provide a JSON configuration file path or a JSON string via environment variables.

export CONFIG_PATH=mcp_server/mcp_config.json
export CONFIG='{"name":"value"}'
export SECURITY='API_KEY=your_api_key'

Additional setup and notes

If you plan to run tests or perform static analysis, you can use the available scripts for linting, type checking, and testing.