Introducing the SQL MCP Server
summary
Open source SQL MCP Server (aka data API builder) provides a JSON-configured, containerized API front end for SQL Server, Azure SQL, PostgreSQL, Cosmos DB and MySQL, running cloud or on‑prem and powering Microsoft Fabric’s GraphQL at scale. A cross‑platform CLI (dab init) scaffolds a config that enables REST, GraphQL and an MCP surface simultaneously, collapses hundreds of CRUD tool choices into seven tools (describe/create/read/update/delete/execute/aggregate), enforces policies/RLS, and ships free with VS Code integration.
AI-written summary · about
chapters (18)
- 0:00SQL MCP Server intro
- 1:13Why devs need better DB APIs
- 3:59Problem with CRUD APIs
- 5:46Data API Builder features
- 10:03MCP servers for AI agents
- 13:07SQL MCP Server: one engine, two names
- 14:32Configuring Data API Builder
- 21:58Running in container
- 24:03REST and GraphQL endpoints
- 29:44Security and auth options
- 33:53MCP tools and limits
- 37:23Query multiple DBs with one API
- 40:58Deployment and CI/CD
- 44:53Use cases: microservices, BaaS, CQRS
- 47:17VS Code extension and tools
- 50:50Omnibus and Aspire integration
- 53:38Problems solved by Data API Builder
- 54:41Resources and next steps
related talks
46mMCP for LLM Agents, Infrastructure APIs & Data Services
44mGetting started with MCP Toolbox for Databases
30mLet's make an MCP Server!
24mAn MCP for your Postgres DB
35mMCP in Action: Real-World Use Cases & Design Patterns
01h 01m.NET Meets MCP: Build Your Own AI-Powered Service with C#
47mMCP Demystified: Cutting Through the Hype-What It Is, What Isn't & Its Role in the Agentic RAG Stack
30mComposable AI: Building Next-Gen AI Agents with MCP