$ loading_
Let AI safely query and manage DuckDB databases through MCP tools.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "mcp-server-duckdb" yet — see the docs or source repo.
Connect to the DuckDB database, inspect the available schemas and tables, then write SQL to calculate sales, order counts, and average order value by region for the last 12 months, sorted by sales descending.
Returns a schema overview, executable SQL, and a regional summary of the results.
Import /data/events.csv into DuckDB, create a cleaned events table with normalized timestamps, deduplicated rows, and empty user IDs removed, then generate a daily active users summary table.
Returns the SQL for import and table creation, processing steps, and details of the generated tables.
Connect to the database in read-only mode, list all schemas, tables, column types, and primary key information, and identify which tables are best suited for user retention analysis.
Returns a schema inventory, key table notes, and recommended tables for retention analysis with reasons.
Connect to DuckDB via MCP for queries, table creation, and schema inspection.
A persistent DuckDB MCP server lets AI assistants query CSV, Parquet, and cloud data in natural language.
Safely let AI inspect database schemas and query PostgreSQL and MySQL data.
Safely explore and query SQLite databases using natural language.
Query SQL databases safely in natural language with validated read-only access.
Let AI query multiple SQL databases read-only and export results.