A demo MCP server with two governed systems (pipeline semantic layer and predictive model) for querying and scoring professional services opportunities with cross-system governance.
Exposes a professional services pipeline prediction model with tools to score opportunities, validate inputs, and retrieve model metadata such as win probability, fees, and margin.
Exposes a governed semantic layer built on dbt Core and DuckDB, enabling AI agents to query predefined metric definitions for a P&C insurance dataset. Prevents metric hallucination by restricting agents to governed tools and read-only data access.