# Introducing the SQL MCP Server - Jerry Nixon - NDC Toronto 2026

## Executive summary

SQL MCP Server, an open-source component from Microsoft's data API builder, provides a secure and standardized abstraction layer for modern applications, especially those powered by AI agents. It allows external models to interact with enterprise databases (including SQL Server, PostgreSQL, Cosmos DB, and MySQL) without requiring direct T-SQL knowledge or exposing sensitive connection strings. The solution standardizes database access into three endpoints—REST, GraphQL, and MCP—simplifying the development process and significantly enhancing security by enforcing policies at the API layer.

## Key takeaways

- Unified Data Access Layer: The SQL MCP Server acts as a single point of entry for all data interactions, supporting multiple database types (SQL, NoSQL) and exposing three standardized APIs: REST, GraphQL, and the specialized Model Control Protocol (MCP). This abstraction layer allows developers to write code against the API surface rather than directly against the underlying schema.
- AI Agent Integration via MCP: For AI agents, which cannot speak directly to a database, the MCP endpoint is critical. It collapses the potential hundreds of CRUD tools (one per table) into a standardized set of seven tools (Describe Entities, Create, Read, Update, Delete, etc.), preventing model overload and ensuring reliable agentic workflows.
- Simplified Development & CI/CD: The solution aims to eliminate the need for boilerplate CRUD API code in a codebase. By using data API builder, developers can significantly reduce complexity and potential errors, streamlining the CI/CD pipeline while maintaining high functionality.
- Advanced Security & Policy Enforcement: Security policies (like Row-Level Security) can be enforced at the API layer, even if structural changes are impossible in the underlying database. Furthermore, it supports advanced authentication methods like OpenID Connect and On Behalf Of (OBO) pass-through authentication.

## Technical details

- Data API Builder Architecture: The system is containerized, running as a cross-platform HTTP endpoint that accepts configuration via a JSON file. This configuration defines the data source connection string and explicitly lists which components (tables, views) are exposed to the API.
- API Capabilities: The platform supports three primary interaction methods: REST (JSON/HTTP), GraphQL (querying a schema using simple nested queries, allowing joins between tables automatically), and MCP. The configuration file allows these capabilities to be enabled or disabled independently.
- Deployment & Scaling: The solution is designed for enterprise scale, having been used by Microsoft Fabric (a large data application). It can run in various topologies (cloud/on-premises) and supports advanced patterns like CQRS (separating read/write concerns) and multi-database querying within a single payload.
- Core Commands: Key commands include `dab init` (to create the initial configuration file), `dab add [table]` (to register database entities), and `dab start`/`dab deploy` (for running or deploying the containerized service).

## Practical implications

- Reduces the dependency on specialized T-SQL knowledge by allowing developers to interact with data using only JSON and HTTP.
- Simplifies multi-cloud deployments by providing a standard API surface that can be swapped between different database types (e.g., PostgreSQL to Azure SQL) without changing application code.
- Enables secure, programmatic access for AI agents, solving the problem of connecting LLMs to structured data in a controlled manner.

## Topics

SQL, Data API, GraphQL, REST, AI Agents, Containerization, Security Policies, Microservices Architecture, data API builder, SQL MCP Server, Microsoft Fabric APIs

Source: https://www.youtube.com/watch?v=qJCkC4wZG6E