M

MotherDuck MCP

Query DuckDB and MotherDuck with natural language

Official
Databases
Install Command
npx -y mcp-server-motherduck
Claude Desktop Config
{
  "mcpServers": {
    "motherduck": {
      "command": "npx",
      "args": ["-y", "mcp-server-motherduck"],
      "env": { "motherduck_token": "<TOKEN>" }
    }
  }
}

MotherDuck MCP is an officially maintained MCP server in the Databases category, developed by MotherDuck. It runs locally on your machine, keeping your data private and giving you full control over the connection. This makes it easy to query and manage your data without leaving your AI assistant.

About MotherDuck MCP

MotherDuck MCP integrates AI assistants with MotherDuck and local DuckDB databases for fast analytical queries.

Features

  • Connect to MotherDuck cloud or local DuckDB
  • Execute SQL analytical queries
  • Access Parquet, CSV, and JSON files directly
  • In-process columnar analytics
  • Share databases across sessions
  • OLAP-optimised for data analysis

Who Should Use MotherDuck MCP?

  • 1Run natural-language queries against your database without writing SQL
  • 2Inspect schemas, tables, and relationships during development
  • 3Automate data exports, migrations, and reporting tasks
  • 4Let AI assistants answer questions directly from your live data

How to Install MotherDuck MCP

Before you start

You will need Node.js (v18 or later) installed on your machine — download it from nodejs.org if you haven't already.

  1. 1Open a terminal (Terminal on Mac, Command Prompt or PowerShell on Windows).
  2. 2Paste the install command above and press Enter — Node.js will download and run the server automatically.
  3. 3Add the server to your Claude Desktop config file (see the JSON snippet above) and restart Claude.

The Claude Desktop config snippet above can be copied and pasted directly into your claude_desktop_config.json file — no editing required.

How MotherDuck MCP Compares

It is an officially maintained server — unlike community alternatives, it is built and supported by the original project team, ensuring compatibility with upstream changes.
It runs entirely on your local machine, so no data leaves your environment — important for teams with privacy or compliance requirements.
Authentication uses API keys, giving you fine-grained control over access without requiring a full OAuth setup.

Tags

duckdbmotherduckanalyticssqlolap