An MCP server gives an LLM a standard way to reach your data and run tools against it. Every API is built differently, and the Model Context Protocol puts one interface over all of them, which is why Anthropic's standard gets compared to USB C.

This episode covers what the standard defines, how tools and resources set the boundaries on what an AI can do with your systems, and what you get by writing a server yourself. We built one for our own AI-ready data model and hit a context problem along the way: the model would skip the business context files and bluff its way through an answer, then admit it never read them when asked directly. The fix was a token buried in those documents that the server checks before it will run any other tool.

If you work in data, BI, or analytics engineering and you are weighing a vendor's MCP server against building your own, start here.

Like and subscribe for straight talk on data, AI, and running a modern business on real numbers.

Blue Margin builds and manages data platforms on Microsoft Fabric and Power BI for mid-market and private equity backed companies. Our Managed Data Service consolidates your systems into one governed source, delivers the dashboards your team runs on, and maintains them as your business changes. Learn more at bluemargin.com.

The platinum layer sits on top of the standard medallion architecture, built specifically to get data ready for LLMs. In this episode, Brick and Landon break down what it takes to build one well.

Landon walks through the two foundations that make a platinum layer work: markdown files that give the LLM business context and call out data gotchas, and a modeling approach that goes further than typical BI denormalization. They discuss why AI models need a single grain of data to avoid summing errors, why report-specific columns need to be stripped out, and why the platinum layer gets materialized nightly instead of served through views.

They also cover the role of MCP servers in this setup, including why Blue Margin builds tightly scoped servers for business users asking direct questions and more open ones for analysts building queries.

If you've been wondering what actually separates a working AI data layer from a frustrating one, this episode covers the fundamentals.

Key Moments:

1:00 — Markdown Files & Context
2:05 — What Happens Without Context
2:58 — Fabric Data Agent Test
3:19 — Modeling for AI
4:25 — The Grain Problem
5:11 — Extreme Denormalization
5:28 — Cleaning Columns & Tables
6:37 — Nightly Materialization
7:43 — Why You Need an MCP Server
8:22 — Two Types of MCP Access

About Blue Margin

Blue Margin is a Microsoft Fabric and Power BI consultancy based in Fort Collins, Colorado. We help mid-market and private equity-backed companies build data platforms that hold up: clean architecture, trustworthy reporting, and dashboards teams actually use. The Dashboard Effect is where we talk through the technical decisions behind that work.

Learn more: https://bluemargin.com

The gold layer is where cleaned, validated data lives in a medallion architecture, ready for reporting and analysis. In this episode, Brick and Landon break down what actually makes a gold layer good.

Landon covers what "good" means in practice: deduplicated data, validated numbers, and a structure business users can trust without checking behind the curtain. They discuss why star schema still holds up as the standard modeling approach, how to handle naming conventions that make sense to analysts instead of source systems, and what happens when six different systems all claim to have "the customer table."

They also get into the messier parts of building a gold layer: matching source system reports to catch hidden filters, deciding how to relate keys across systems without collapsing records that only look the same, and building exception reports to flag duplicates back to the business instead of quietly fixing them downstream.

If you've ever wondered what separates a gold layer that works from one that just exists, this episode covers the fundamentals.

Key Moments:

0:36 — What is the gold layer?
1:00 — Combining data silos
2:01 — Modeling the gold layer
2:22 — A preview of the platinum layer
2:30 — Naming conventions
3:39 — D_ and F_ naming standards
4:08 — Validating the gold layer
4:36 — Hidden filters and reporting errors
5:13 — Relating fact tables
5:57 — Handling duplicates
6:52 — Exception reports

About Blue Margin

Blue Margin is a Microsoft Fabric and Power BI consultancy based in Fort Collins, Colorado. We help mid-market and private equity-backed companies build data platforms that hold up: clean architecture, trustworthy reporting, and dashboards teams actually use. The Dashboard Effect is where we talk through the technical decisions behind that work.

Learn more: https://bluemargin.com