"DuckDB" matching MCP servers:

Enables natural-language-driven analytics over CSV/Parquet or built-in data by decomposing questions into analytical tasks, running them via deterministic DuckDB and SciPy tools, and publishing only claims verified against the underlying rows.

Enables autonomous data quality inspection and repair workflows. It scans DuckDB warehouses for anomalies, generates and verifies fixes in a dry-run copy, then applies them after validation, with full audit logging.

Persistent memory for AI agents with Ebbinghaus forgetting curve, semantic graph retrieval, and engineering state tracking. Local-first, DuckDB, zero cloud dependency.