MCP Server Motherduck

🚀 MotherDuck MCP Server Documentation (English Version)

This documentation provides a guide on installing, configuring, and using the MotherDuck MCP server. It also includes troubleshooting steps and license information.

🚀 Quick Start

The following sections will guide you through the installation and configuration process using different tools.

📦 Installation

Using Claude Desktop

1. If you haven't installed Claude Desktop yet, download and install it from claude.ai/download.
2. Open the configuration file for Claude Desktop:
   • On your first use, you can open it directly within the Claude Desktop application. Select "Settings", go to the "Developer" tab, and click the "Edit Configuration" button.
   • Add the following configuration to the claude_desktop_config.json file:

{
  "mcpServers": {
    "mcp-server-motherduck": {
      "command": "uvx",
      "args": [
        "mcp-server-motherduck",
        "--db-path",
        "md:",
        "--motherduck-token",
        "<YOUR_MOTHERDUCK_TOKEN_HERE>"
      ]
    }
  }
}

⚠️ Important Note

• Replace <YOUR_MOTHERDUCK_TOKEN_HERE> with your actual MotherDuck token.
• Set the --home-dir parameter as needed (e.g., --home-dir /Users/your_username).

Using VS Code

You can add the following configuration to the .vscode/mcp.json file or copy this content directly into the mcp.json file in your workspace:

{
  "inputs": [
    {
      "type": "promptString",
      "id": "motherduck_token",
      "description": "MotherDuck Token",
      "password": true
    }
  ],
  "servers": {
    "motherduck": {
      "command": "uvx",
      "args": [
        "mcp-server-motherduck",
        "--db-path",
        "md:",
        "--motherduck-token",
        "${input:motherduck_token}"
      ]
    }
  }
}

💻 Usage Examples

Basic Usage

After configuration, you can ask Claude to perform the following operations:

• "Create a new database and table in MotherDuck"
• "Query data from a local CSV file"
• "Join data from a local DuckDB database with a table in MotherDuck"
• "Analyze data stored in Amazon S3"

Advanced Usage

Connecting to the Default MotherDuck Database

To connect to the default MotherDuck database, use the --motherduck-token parameter to specify the token:

uvx mcp-server-motherduck --db-path md: --motherduck-token <your_motherduck_token>

Connecting to a Specified MotherDuck Database

uvx mcp-server-motherduck --db-path md:your_database_name --motherduck-token <your_motherduck_token>

Connecting to a Local DuckDB Database

uvx mcp-server-motherduck --db-path /path/to/your/local.db

Connecting to an In - Memory Database

uvx mcp-server-motherduck --db-path :memory:

If the database path is not specified but the motherduck_token environment variable is set, the server will automatically connect to the default MotherDuck database (md:).

Running in SSE Mode

To run the server in SSE mode, use the supergateway tool:

npx -y supergateway --stdio "uvx mcp-server-motherduck --db-path md: --motherduck-token <your_motherduck_token>"

🔧 Troubleshooting

⚠️ Important Note

1. Ensure that all dependencies are correctly installed.
2. Check the command syntax for correctness.
3. If you encounter the spawn uvx ENOENT error, confirm that the uvx tool is correctly installed and in the system path.

📄 License

This project is licensed under the MIT License. For more information, please refer to MIT License.