MCP100 Assessment

Editorial verdict

Expose governed Microsoft SQL data operations through Data API Builder and MCP.

Reviewed 2026-07-30 · Next review 2026-09-15

Task Fit

Mapped

Working with structured data

Trust

Status warning

distribution_identity; operating_history

Maintenance

Date unavailable

No dated repository or package update is currently stored.

Popularity

Signals unavailable

No independently comparable adoption metric is currently stored.

Best for

Production-oriented SQL Server and Azure SQL workflows with role-based controls.

Not ideal for

Production use before the documented maturity gaps are resolved

Avoid if

The connected identity is broader than the task requires
Tool calls cannot be reviewed before consequential mutations

Trade-offs

The product is new and an exact standalone distributable identity was not confirmed during this review.

Evidence scope

Evidence

Current source snapshot

Popularity

No MCP-specific repository metric is stored

No MCP-specific package metric is stored

Stars observation date unavailable · Downloads observation date unavailable

The publisher provides a hosted implementation without a separate public repository metric.

The publisher does not document a separate comparable package metric for this implementation.

Maintenance

Publisher activity observed 2026-07-30T19:00:00.000Z

Current source snapshot

Trust review

Source relationship: First-party MCP

Reviewed 2026-07-30 · Next review 2026-09-15

Evidence source 1 ↗

Evidence-backed setup

Install & Agents

Choose your MCP client. A client connects to the MCP server; the language model is selected inside that client. Only stored, source-backed configurations are shown.

Claude Code

Local stdio

MCP100 logic checked

claude mcp add sql-mcp-server -- dab "start" "--mcp-stdio" "role:anonymous" "--config" "/absolute/path/to/dab-config.json" "--LogLevel" "error"

The publisher connection details were combined with this client's official MCP transport configuration; installation was not executed by MCP100.

Verify safely: Restart Claude Code, confirm sql-mcp-server tools are listed, and perform one read-only test with non-sensitive data.

Uninstall and revoke

Remove sql-mcp-server from Claude Code, restart the client, remove any separately installed package, and revoke dedicated credentials if used.

Evidence & methodology

Publisher-documented setup is not the same as MCP100 execution testing. “MCP100 logic checked” means the stored configuration shape was reviewed, not that third-party MCP software was run.

Evidence checked 2026-08-12

Evidence 1 ↗Evidence 2 ↗

Loading optional publisher installation details…

Capability

What it does

Expose governed Microsoft SQL data operations through Data API Builder and MCP.

Data & DatabasesSoftware & Technology

Representative uses

Production-oriented SQL Server and Azure SQL workflows with role-based controls.

Important limits

Production use before the documented maturity gaps are resolved

Tools7 toolsView tools

describe_entities
Describe entities configured in Data API Builder.
create_record
Create a record through a configured entity.
read_records
Read records through a configured entity.
update_record
Update a record through a configured entity.
delete_record
Delete a record through a configured entity.
execute_entity
Execute a configured entity operation such as a stored procedure.
aggregate_records
Aggregate records for a configured entity.

Data API Builder 2.0 documents seven built-in DML tools.

Source: Official documentation

Context Footprint

Varies by configuration

Estimated token footprint of the MCP tool schemas exposed to the agent.

~1,400 schema tokens is an Approx. catalog/reference estimate, not Runtime Verified.

Reviewed access

Access & risk

Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.

Authentication: Microsoft documents enterprise database authentication and API-layer controls.
Permissions: Database roles, Data API Builder configuration, and SQL permissions govern accessible objects and operations.
Data handling: Authorized service data and tool results pass through the MCP server to the connected AI client. Review the publisher and client data policies before using sensitive data & databases information.
Cost: The MCP integration has no separately verified MCP100 price conclusion. Publisher subscriptions, API usage, compute, storage, and AI-client charges may apply.
Risk and cautions: The product is new and an exact standalone distributable identity was not confirmed during this review. Use a test environment where practical, least-privilege credentials, narrowly enabled tools, and explicit confirmation for mutations. MCP100 did not execute third-party server code during this documentation review.

Related reviewed MCPs

Other options

Google MCP Toolbox for Databases

MCP100 Selected

Connect MCP clients to enterprise databases with prebuilt or explicitly defined tools.

Choose this instead if

Choose Google MCP Toolbox for Databases instead if schema exploration and database-aware coding in development environments.

Connect MCP clients to enterprise databases with prebuilt or explicitly defined tools.

Compare with Microsoft SQL MCP Server View Google MCP Toolbox for Databases details

Redis MCP

MCP100 Selected

Manage and search Redis data through Redis's MCP server.

Choose this instead if

Choose Redis MCP instead if inspecting and manipulating Redis strings, hashes, lists, sets, sorted sets, streams, JSON, and search indexes.

Manage and search Redis data through Redis's MCP server.

Compare with Microsoft SQL MCP Server View Redis MCP details

Supabase MCP

MCP100 Selected

Connect AI tools to Supabase projects and development workflows.

Choose this instead if

Choose Supabase MCP instead if inspecting one Supabase project's schema, logs, advisors, and docs.

Connect AI tools to Supabase projects and development workflows.

Compare with Microsoft SQL MCP Server View Supabase MCP details

Read publisher documentation

Publisher documentation

Official Docs

Original product, capability, tool, and usage documentation from the MCP publisher. Installation sections appear under Install & Agents.

View original documentation ↗

Title: SQL MCP Server Documentation - SQL MCP Server

URL Source: https://learn.microsoft.com/en-us/sql/mcp/

Markdown Content: Skip to main content

Microsoft Ignite

November 17–20, 2026

Interactive learning, certifications, and direct access to experts all in one place.

Register now

Dismiss alert

This browser is no longer supported.

Upgrade to Microsoft Edge to take advantage of the latest features, security updates, and technical support.

Download Microsoft Edge More info about Internet Explorer and Microsoft Edge

Learn

Suggestions will filter as you type

Sign in

Sign out

Learn

Documentation

Register now

Microsoft Ignite | November 17-20, 2026 Interactive learning, certifications, and direct access to experts all in one place.

Training & Labs

Register now

Microsoft Ignite | November 17-20, 2026 Interactive learning, certifications, and direct access to experts all in one place.

Q&A

Register now

Microsoft Ignite | November 17-20, 2026 Interactive learning, certifications, and direct access to experts all in one place.

Topics
- Agents Key concepts and resources for agentic computing
- Artificial intelligence Curated resources for AI fluency with apps and services
- DevOps DevOps practices, Git version control and Agile methods
- Learn for Organizations Curated offerings from Microsoft to boost your team’s technical skills
- Security Guidance to help you tackle security challenges
- Startups hub Technical guidance to move toward enterprise readiness
- Assessments Interactive guidance with custom recommendations
- Student hub Self-paced and interactive training for students
- Educator center Resources for educators to bring technical innovation in their classroom

Register now

Microsoft Ignite | November 17-20, 2026 Interactive learning, certifications, and direct access to experts all in one place.

Suggestions will filter as you type

Sign in

Sign out

SQL

Overview
- On-premises
  - SQL Server on Windows
  - SQL Server on Linux
- Azure
- What's new

Azure Portal Download SQL Server

SQL MCP Server documentation

Enable AI agents to safely interact with SQL databases using Model Context Protocol. Built on Data API builder, SQL MCP Server provides deterministic, secure, and production-ready database operations for agentic applications.

Overview

Introduction to SQL MCP Server

Architecture

Data manipulation tools

Deploy

Deploy to Azure Container Apps

How-To Guide

Add descriptions to entities

Reference

Data API builder documentation

Concept

Model Context Protocol specification

Get started with SQL MCP Server

Deploy SQL MCP Server locally or to the cloud and connect it to your AI applications using these quickstart guides.

Core concepts

Understand how SQL MCP Server enables AI agents to interact with databases safely using Model Context Protocol and Data API builder's proven architecture.

Model Context Protocol (MCP)

Learn how MCP provides a standard way for AI agents to discover and call external tools with predictable inputs, outputs, and behavior.

Data manipulation tools

Explore the six DML tools that SQL MCP Server exposes to AI agents for typed CRUD operations with full RBAC support.

Data API builder

SQL MCP Server is built on Data API builder's entity abstraction layer, leveraging proven RBAC, caching, and telemetry capabilities.

SQL MCP Server is Microsoft's open-source solution for bringing AI agents into your data workflows. Built on Data API builder's proven entity abstraction, RBAC, and telemetry, SQL MCP Server provides a production-ready surface that works consistently across REST, GraphQL, and MCP.

Get started today with the Visual Studio Code quickstart or deploy to Azure Container Apps for production workloads.

English (United States)

Your Privacy Choices

Theme

Loading optional publisher documentation…

FAQ

What can Microsoft SQL MCP Server do?

MCP100's current stored description says: Expose governed Microsoft SQL data operations through Data API Builder and MCP.

Can Microsoft SQL MCP read and write database data?

MCP100's current stored permissions review says: Database roles, Data API Builder configuration, and SQL permissions govern accessible objects and operations.

Does Microsoft SQL MCP work with Codex?

Yes. MCP100 found MCP100 logic checked setup for Codex. The current reviewed evidence also documents setup for Claude Code, Claude Desktop, VS Code, Cursor, and OpenCode. This reflects setup evidence, not an MCP100 execution test or a guarantee that a current client will connect.

How does Microsoft SQL MCP authenticate?

MCP100's current stored authentication review says: Microsoft documents enterprise database authentication and API-layer controls.

Is Microsoft SQL MCP safe to use with a production database?

MCP100's current stored risk review says: The product is new and an exact standalone distributable identity was not confirmed during this review. Use a test environment where practical, least-privilege credentials, narrowly enabled tools, and explicit confirmation for mutations. MCP100 did not execute third-party server code during this documentation review. This MCP is not a security boundary or a general security certification.

Is this an official MCP?

Microsoft is listed as First-party MCP in MCP100’s current evidence.

Current official resources:

Publisher documentation ↗