While many organizations remain stuck in pilots and proofs-of-concept, one of our clients is operationalizing AI… and feeling the benefits.

Using Model Context Protocol (MCP), EMC Insurance connected their siloed data systems into a single interface; allowing AI tools to easily connect with and harness their data, and massively speed up complex engineering work.

This month, we're showing you EMC’s use cases for MCP so that you can understand how this technology can unlock AI value at your organization.

Was this email forwarded to you? Subscribe here >

Real MCP Results: dbt Migration 

From 4,000 Hours to 4 Weeks

"There’s been value in every use case we’ve done. But if you can find a few slam dunks like this, it [MCP] makes everything worthwhile."

- Rob Vicker, Data Architecture Director, EMC Insurance

EMC Insurance was facing a 4,000-hour project to manually migrate their warehouse to dbt.

Four weeks later, with one person, they were 96% done, thanks to Model Context Protocol (MCP).

EMC Insurance has embraced MCP to accelerate extremely complex data management initiatives to create meaningful cost and time savings and put more focus on strategic work.                                                                                                                                             

Here are 3 ways EMC is using MCP to operationalize AI:

• Large-scale dbt migration: Converted 130 SQL views into ~1,000 dbt models with 96% accuracy. The data leaders had estimated 3,000-4,000 hours of manual work. The reality with MCP: It took 4 weeks using one person.
• Power BI metadata analysis: Unified scattered metrics across dozens of reports into a single source of truth. A previous manual attempt ran for 7 months before the team had to abandon it. With MCP, they completed it in days.
• Data lineage mapping: Built instant data discovery across their entire Snowflake schema using plain English queries. They can now ask questions like, "What is total reimbursement for 2025? Show all tables and fields needed to calculate it" and get immediate answers. What typically took a data engineer several hours per query now happens in seconds. A previous team spent 11 months trying to build similar functionality before giving up.

"To make that much progress in 4 months on bleeding edge technology is seriously impressive. This has the potential to change how you think about executing data analytics projects in the future."

- Kevin Lobo, Analytics8 EVP of Consulting

Curious about how MCP works? 

Learn about our client’s MCP implementation strategy from concept to production, and get the prerequisites to start leveraging MCP for your own data initiatives.