Data architecture reference

How your data reaches Claude

The full path data takes — from your source database, through Microsoft Fabric mirroring, to Claude generating visualizations — and the role the MCP server plays in the middle.

Source databaseYour operationalSQL database Fabric MirroringContinuous replicationinto OneLake (Deltatables), read-only SQL analyticsendpointQuery mirrored datawith normal T-SQL SQL MCP ServerData API BuilderExposes fixed toolsover HTTP (localhost)runs on your machine Claude DesktopChat app on your laptop,calls MCP tools on request Shared Claude ProjectCustom instructions +connector pre-enabledone per person, same setup Team membersEach signs in once,asks in plain English

Currently being tested in a personal project on one desktop before rolling out as the shared version shown above.

The six layers, in order

Each box in the diagram above corresponds to one of these.

01

Source database

The live, operational SQL database that runs the business day to day. This is the system of record; nothing downstream ever writes back to it.

02

Fabric Mirroring

A managed Microsoft service that continuously copies data into OneLake as Delta tables, without adding load to the source database.

03

SQL analytics endpoint

An auto-generated, read-only, standard T-SQL interface on top of the mirrored data — this is what Data API Builder actually connects to.

04

SQL MCP Server

The translation layer between Claude and the database — covered in detail below. This is the piece that makes the whole thing possible.

05

Claude Desktop

The chat app itself. It holds the connector to the MCP server and calls its tools whenever a conversation needs live data.

06

Shared Claude Project

A persistent workspace with custom instructions and the connector pre-loaded for every team member. Each person gets a private copy of the same setup — nobody edits a config file; they just open the project and get guided from there.

What is the MCP server actually doing?

MCP (Model Context Protocol) is an open standard that lets Claude connect to external tools and data sources. An "MCP server" is a small program that exposes a fixed, predefined set of actions — called tools — that Claude is allowed to call.

Here the MCP server is Data API Builder (DAB), running locally via dab start. It connects to the Fabric SQL analytics endpoint on one side and exposes a small set of database tools to Claude on the other. It does not let Claude run arbitrary SQL — a deliberate safety design. Claude can only call these tools, each scoped to the tables you explicitly added:

read_recordsFetch rows from a table, with filters
aggregate_recordsSums, counts, averages, grouped
describe_entitiesList available tables and columns
execute_entityRun a named, pre-approved query

Because every table was added with "anonymous:read" permissions, none of these tools can create, modify, or delete anything — the connection is read-only end to end.