Submit Log in

MotherDuck / DuckDB

by MotherDuck

1 views

v1.0.7

Repository Docs

Databases & Data

analyticsduckdbsqldata

Summary

Run DuckDB analytics locally or in MotherDuck's cloud — query files and warehouses with the same SQL.

Features

Analytical SQL over local DuckDB files or MotherDuck cloud
Query Parquet, CSV, and JSON directly without loading
Read-only mode for safe exploration

Installation

Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.

Any MCP-compatible agent

Most agents (Claude, Cursor, Windsurf, VS Code, and more) read a standard mcpServers configuration.

Open your agent's MCP configuration file.
Merge the snippet below into it.
Restart the agent — the "MotherDuck / DuckDB" tools will be available.

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

Claude Code

Add the server with a single CLI command.

claude mcp add motherduck -- uvx mcp-server-motherduck --db-path md:

Claude Desktop

Add the server to claude_desktop_config.json (Settings → Developer → Edit Config).

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

Cursor

{
  "command": "uvx",
  "args": [
    "mcp-server-motherduck",
    "--db-path",
    "md:"
  ]
}

Windsurf

{
  "command": "uvx",
  "args": [
    "mcp-server-motherduck",
    "--db-path",
    "md:"
  ]
}

VS Code

{
  "command": "uvx",
  "args": [
    "mcp-server-motherduck",
    "--db-path",
    "md:"
  ]
}

Description

The MotherDuck MCP server gives an assistant a full analytical SQL engine, working against local DuckDB databases, MotherDuck's cloud warehouse, or files on disk and in object storage.

What makes DuckDB a good fit here

You can query a Parquet, CSV, or JSON file directly — no import step, no schema definition. That means an assistant can answer questions about a data file the moment it exists, which removes most of the friction from ad-hoc analysis.

Capabilities

SQL execution with DuckDB's full analytical feature set — window functions, CTEs, complex joins
File querying across local paths and S3 and other object stores
MotherDuck cloud for shared, persistent warehouses
Hybrid execution, combining local files with cloud tables in one query
Read-only mode for exploration you do not want writing anything

Setup

uvx mcp-server-motherduck --db-path md: for the cloud service with a MotherDuck token, or a local file path for pure DuckDB use.

Related MCP Servers

MCP: deja-vu

by Vladislav Shulcz

New

Indexes the coding-agent sessions already sitting on your disk — months of history from before you installed it — and serves them back over MCP. 3.5 GB searched in ~1.5 ms, no LLM, no embeddings.

Developer ToolsDatabases & Data

MCP: Weaviate MCP Server

by Weaviate

New

Weaviate's MCP server, built into the database itself — hybrid search, schema inspection, tenant listing and batch upserts at /v1/mcp, scoped by RBAC.

Databases & Data

MCP: MCP Toolbox for Databases

by Google

New

Google's open-source MCP server for enterprise databases — one binary that fronts AlloyDB, BigQuery, Spanner, Postgres, MySQL, Oracle, MongoDB, Snowflake and more.

Databases & DataCloud & Infrastructure

MCP: DBHub

by Bytebase

Featured

A universal database MCP server — one integration for PostgreSQL, MySQL, SQL Server, SQLite, and MariaDB.

Databases & Data

Browse all MCP servers →