MotherDuck / DuckDB MCP Server
MCP servers for DuckDB and MotherDuck: a managed remote server at api.motherduck.com/mcp and an open-source local server for DuckDB files, in-memory DBs and S3.
Tags
Description
Remote (managed): https://api.motherduck.com/mcp over HTTP, OAuth for most clients or Authorization: Bearer <motherduck_token> for backend clients; runs read-only and read-write SQL, explores schemas, attaches shares, answers DuckDB/MotherDuck docs questions, and manages Dives, Flights and Guides. Local (this repo): uvx mcp-server-motherduck --db-path ... connects to local DuckDB files (read-only by default), in-memory databases, S3-hosted databases or MotherDuck, and can read from and write to the local filesystem. MotherDuck itself has a Lite plan from $0 and a Business plan at $250 per org per month plus usage.
Agent access
Related
- ClickHouse MCP Server: ClickHouse's official MCP server: run SQL, list databases and tables on a ClickHouse cluster (read-only by default), with optional embedded chDB queries.
- Postgres MCP Pro: Open-source Postgres MCP server with database health checks, index tuning, EXPLAIN plans with hypothetical indexes, schema intelligence and safe, configurable SQL execution.
- MCP Toolbox for Databases: Google's open-source MCP server for databases: prebuilt tools for MCP clients plus a framework for defining secure custom database tools for agents.
- Neon MCP Server: Lets AI assistants manage Neon serverless Postgres projects and databases through the Neon Management API.
Guides & comparisons
- Data analysis agent stack (Stack): An agent that answers questions from your data: it queries DuckDB files, a ClickHouse warehouse or Postgres through read-only MCP servers, runs heavier analysis in a sandbox, reads spreadsheets and PDFs, and is tested and traced so you can trust the numbers.
Sources
- https://motherduck.com/docs/sql-reference/mcp/
- https://github.com/motherduckdb/mcp-server-motherduck
- https://motherduck.com/product/pricing/
Machine-readable
- JSON
- Markdown
- Source file on GitHub (edit via pull request)