# MotherDuck MCP server
> Query, explore and manage MotherDuck cloud databases with DuckDB SQL from your AI assistant.
- Listing: https://mcp.tc/i/motherduck
- Connect: use the server's own URL `https://api.motherduck.com/mcp` (OAuth sign-in at the server); clients connect to it directly. The listing link is a page, not an MCP endpoint.
- Type: remote (Streamable HTTP)
- Auth: OAuth sign-in
- Category: [Databases & Backend](https://mcp.tc/c/databases)
- Vendor: MotherDuck
- Homepage:
- Docs:
- Repository:
- Package: pypi `mcp-server-motherduck`
## About
Connects an assistant to MotherDuck, the cloud service built on DuckDB. It can run SQL queries, list databases, tables and views, and inspect column definitions so answers come from your real data.
The hosted endpoint at https://api.motherduck.com/mcp uses streamable HTTP and OAuth sign-in with a MotherDuck account. A local alternative, the mcp-server-motherduck package, runs with uvx and can also open in-memory DuckDB, local DuckDB files and S3-hosted databases. It is read-only by default, and a MotherDuck token is needed to reach MotherDuck from it.
## What it can do
- Run SQL queries against MotherDuck and DuckDB databases
- List available databases
- List tables and views in a database
- Inspect columns of a table or view
- Switch between database connections in the local server when enabled
## Tools (5)
- `execute_query`: Run a SQL query; unqualified table names resolve automatically.
- `list_databases`: List all databases, useful with multiple attached DuckDB databases or MotherDuck.
- `list_tables`: List all tables and views, defaulting to the current database.
- `list_columns`: List all columns of a table or view in the current database or schema.
- `switch_database_connection`: Switch to a different database connection; needs the --allow-switch-databases flag.
## Example prompts
- "List the databases in my MotherDuck account."
- "Show the columns of the orders table and summarize its structure."
- "Run a SQL query for monthly revenue by region from my sales database."
- "Which tables in my analytics database contain a user\_id column?"
## Install
### Claude Code
1. Run this in a terminal, in your project folder:
```bash
claude mcp add --transport http motherduck https://api.motherduck.com/mcp
```
2. Start Claude Code, type `/mcp`, pick **motherduck** and choose **Authenticate**. A browser window opens for the MotherDuck sign-in.
Add `--scope user` to make it available in every project, not just this one.
### Claude Desktop
1. Open **Settings → Connectors** and click **Add custom connector**.
2. Name it **MotherDuck** and paste this URL:
```url
https://api.motherduck.com/mcp
```
3. Click **Add**, then **Connect**, and sign in when MotherDuck asks.
Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.
### claude.ai
1. Open the connector form on claude.ai. This button fills in the name and URL for you:
[Add to claude.ai]() (opens connector settings)
2. Check that the URL reads `https://api.motherduck.com/mcp` and click **Add**.
3. Click **Connect** and sign in when MotherDuck asks.
Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**.
### ChatGPT
1. On chatgpt.com, open **Settings → Security and login** and turn on **Developer mode**.
2. Go to `chatgpt.com/plugins` and click **+** to create an app for a remote MCP server.
3. Paste `https://api.motherduck.com/mcp` as the server URL and choose **OAuth**. ChatGPT sends you to MotherDuck to sign in.
Developer mode is available on the web for Plus, Pro, Business, Enterprise and Education accounts.
### Cursor
[Add to Cursor]() (opens Cursor)
Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):
`mcp.json`:
```json
{
"mcpServers": {
"motherduck": {
"url": "https://api.motherduck.com/mcp"
}
}
}
```
Cursor shows **Needs login** next to the server. Click it to sign in.
### VS Code
[Install in VS Code]() (opens VS Code)
Or from a terminal:
```bash
code --add-mcp '{"name":"motherduck","type":"http","url":"https://api.motherduck.com/mcp"}'
```
Or commit it to the repo in `.vscode/mcp.json`:
`.vscode/mcp.json`:
```json
{
"servers": {
"motherduck": {
"type": "http",
"url": "https://api.motherduck.com/mcp"
}
}
}
```
VS Code asks you to sign in the first time the server starts.
### Devin Desktop
1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):
`mcp_config.json`:
```json
{
"mcpServers": {
"motherduck": {
"serverUrl": "https://api.motherduck.com/mcp"
}
}
}
```
2. Refresh the MCP server list in Cascade and sign in when asked.
Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers.
### Codex
```bash
codex mcp add motherduck --url https://api.motherduck.com/mcp
codex mcp login motherduck
```
Or edit `~/.codex/config.toml` directly:
`config.toml`:
```toml
[mcp_servers.motherduck]
url = "https://api.motherduck.com/mcp"
```
### Gemini CLI
```bash
gemini mcp add --transport http motherduck https://api.motherduck.com/mcp
```
Then, inside Gemini CLI, run `/mcp auth motherduck` to sign in.
This adds it to the current project. Add `-s user` to use it everywhere.
### Any client
Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file.
```json
{
"mcpServers": {
"motherduck": {
"type": "http",
"url": "https://api.motherduck.com/mcp"
}
}
}
```
Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE.
Client only starts local servers? Bridge it with `npx -y mcp-remote https://api.motherduck.com/mcp`.
## Details
- Server version: 1.0.8
- Last checked: 2026-10-03 (reachable, asks for credentials)
- Listed: 2026-10-03
- Updated: 2026-10-03
---
Source: https://mcp.tc/i/motherduck (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report