MCP Server for MS SQL Server (Data Warehousing)

Intro

Learn about the business value here: MCP Server for BI and Analytics.

The Dataself MCP connector exposes your SQL Server data warehouse to Claude through a secure tokenized URL. Once connected, you can query tables, explore data, and generate reports using plain English — no SQL required. In data warehousing (DW) environments, MCP provides a standardized framework for AI systems to access, understand, and interact with warehouse data in a controlled and intelligent manner.

Modern data warehouses such as from DataSelf contain vast amounts of business-critical information spread across multiple systems, schemas, and data models. While traditional BI and SQL tools require technical expertise to retrieve and analyze data, MCP introduces a conversational and AI-driven approach to data access and analytics.

SQL Server MCP — Setup Guide

Your own MCP for SQL Server

The following are popular approaches to create your own private MCP Server. Please contact us for assistance:

• http://github.com/Azure-Samples/SQL-AI-samples

• http://github.com/RichardHan/mssql_mcp_server

• http://github.com/ConnorBritain/mssql-mcp-server

• http://github.com/0xhubed/mcp-ms-sql-server

DataSelf Cloud MCP for SQL Server (WIP)

Work in progress. Scheduled release in June 2026.

This is a guide to connect Claude to your SQL Server data warehouse. 

This guide covers four steps:

• Step 1 — Request your tokenized MCP URL from Dataself

• Step 2 — Add a custom MCP connector in Claude

• Step 3 — Enable all actions for the connector

• Step 4 — Start querying your data

Prerequisites:

• DataSelf Cloud data warehouse: WIP - contact us.

• DataSelf private-cloud or on-premise data warehouse: WIP - contact us.

 Step 1 — Request Your Tokenized URL from Dataself

Contact your Dataself account manager or administrator to request an MCP access URL for your SQL Server environment. Dataself will generate a unique URL that includes an authentication token — no separate login is needed once you have it.

What to ask for:

• An MCP Server URL for your SQL Server / data warehouse

• Confirmation of which databases or schemas the URL has access to

The URL will look something like: https://mcp.dataself.com/abc123tokenxyz/mcp — treat it like a password and do not share it.

Step 2 — Add a Custom MCP Connector in Claude

Open http://Claude.ai in your browser. Click on Customize in the left sidebar and select Connectors.

In Connectors, click the Add (+) … Add custom connector.

Fill in the connector form with the following values:

Click Add to confirm.

Step 3 — Enable All Actions

After adding the connector, Claude will ask how much access to grant. To allow full query capability, you need to enable all actions.

Find the newly added Dataself MCP - Data warehouse connector in your integrations list. Click it to open its settings and look for the Permissions or Actions section.

Select Always allow (or the equivalent option that grants full tool access). This allows Claude to list tables, run queries, and return results from your SQL Server.

Step 4 — Start Asking Questions

Open a new chat in Claude. The Dataself MCP - Data warehouse connector is now active. You can start with broad exploration questions and then go deeper from there.

Example prompts to get started:

• "What tables are available in the database?"

• "Show me total sales by month for the last 12 months"

• "How many active customers do we have by region?"

• "What is the current inventory level by warehouse?"

• "Compare sales performance this year versus last year by product category"

Claude may ask for your permission the first time it runs a query tool in a new session. Click Allow to proceed. You can also click the tool call to expand and inspect the exact query that was executed.