Exposes schema, lineage, and data-quality trust signals from a SQLite-backed catalog as MCP tools, enabling AI agents to answer grounded questions about datasets without hallucinating.
Exposes Iceberg-backed ontology objects, links, and actions as typed MCP tools for LLM agents, enabling governed data access and operations without raw SQL.
Exposes data query and auto-insights (anomaly detection) as MCP tools. Enables AI agents to query metrics, list columns, and get data insights directly from pandas.