Solving dashboard errors in minutes: How Integral Ad Science used MCP to connect agents to dbt and Databricks

Integral Ad Science (IAS) addressed the "BI why" problem in business intelligence (BI) dashboards, where AI agents struggle to provide context and reasoning behind data metrics, by using Model Context Protocol (MCP) servers to connect AI chatbot agents to dbt and Databricks. At the Databricks Data + AI Summit 2026, Mars Dauer, IAS's Senior Director of Enterprise Data and AI, explained how his team utilized MCP as a universal adapter to quickly integrate new tools without custom API clients, thus enabling AI agents to access and interpret data lineage, validate data, and perform impact analysis effectively. This architecture involved embedding the agent in Looker to streamline context-sharing and employing multiple specialized sub-agents to efficiently handle different tasks, using varied models tailored to specific requirements. The approach has significantly reduced the time analysts spend resolving data issues, showcasing the potential for further enhancements in AI-driven data analysis and management.

Use this post, company, and trend context to find content marketing opportunities, perform competitive analysis, or address product feature gaps via the Plushcap MCP server or the Plushcap API.