What is MotherDuck's DuckDB MCP Server?
An MCP server that connects AI assistants and IDEs to DuckDB's analytical SQL engine. It supports local DuckDB files, in-memory databases, S3-hosted databases, and MotherDuck. Users can execute SQL queries, browse database catalogs, and switch between connections at runtime.
How to use MotherDuck's DuckDB MCP Server?
Install uv via pip install uv or brew install uv, then add a JSON configuration to your MCP client’s config file. Use the command uvx mcp-server-motherduck with args like --db-path :memory: for in-memory, --db-path /path/to/file.duckdb for local files, or --db-path md: for MotherDuck. Additional flags control read-write access, database switching, and security.
Key features of MotherDuck's DuckDB MCP Server
- Execute SQL queries in DuckDB dialect.
- List databases, tables, and columns.
- Switch database connections at runtime (requires
--allow-switch-databases).
- Read-only mode by default for safety.
- Supports local, S3, and MotherDuck databases.
- Configurable row and character limits for results.
Use cases of MotherDuck's DuckDB MCP Server
- Analyze local DuckDB files from an AI assistant.
- Query an in-memory database for development and testing.
- Connect to MotherDuck for cloud-based analytics.
- Ingest or export data between remote databases and local filesystem.
评论