Marketplace for trusted AI agent skills

Skill Detail

Expose database APIs and SQL MCP tools with Azure Data API Builder

Use Azure Data API Builder to generate secure REST, GraphQL, and SQL MCP access for supported databases so agents can query and operate data through bounded tools.

Integrations & ConnectorsMCP
Integrations & Connectors MCP Security Reviewed
⭐ 1.4k GitHub stars
COPY SKILL INSTRUCTIONS (OPTIONAL)
npx skills add agentskillexchange/skills --skill expose-database-apis-and-sql-mcp-tools-with-azure-data-api-builder Copy
Uses the third-party skills CLI, not an ASE-owned installer. Check your agent’s compatibility. This copies instructions; complete the upstream tool setup below separately.
View source Documentation
At a glance
Tools required
.NET 8 or later, Data API Builder CLI, supported database, MCP-compatible agent client
Install & setup
Install .NET 8 or later, run dotnet tool install microsoft.dataapibuilder -g, initialize a dab-config.json with dab init, add database entities and permissions, then run Data API Builder and connect an agent client to the documented SQL MCP server when MCP access is required.
Author
Microsoft Azure
Publisher
Organization
Last updated
Jun 19, 2026
Quick brief

Use Azure Data API Builder when an operator needs to turn an existing SQL Server, Azure SQL, Cosmos DB, PostgreSQL, or MySQL data source into a governed API and agent tool surface. The workflow is to install the dab CLI, create a configuration file for the database connection, define exposed entities and permissions, run the service, and connect an MCP-compatible agent client to the documented SQL MCP server when agent database access is needed. Invoke this instead of using the database or Azure portal directly when a repeatable agent workflow needs bounded REST, GraphQL, or MCP access to data with explicit configuration and authentication. The scope boundary is database access mediation for agents and applications, not a generic Azure product listing or a broad database SDK.

How it works

What this skill actually does

Inputs and prerequisites: .NET 8 or later, Data API Builder CLI, supported database, MCP-compatible agent client.

Setup notes: Install .NET 8 or later, run `dotnet tool install microsoft.dataapibuilder -g`, initialize a `dab-config.json` with `dab init`, add database entities and permissions, then run Data API Builder and connect an agent client to the documented SQL MCP server when MCP access is required.

Source and verification boundary: use https://learn.microsoft.com/en-us/azure/data-api-builder/ as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.

Framework fit: publish this as a MCP workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.