What is Mcp Sql

mcp-sql is a Model Context Protocol server designed to provide comprehensive access to SQL databases, starting with full support for Microsoft SQL Server (MSSQL). It allows AI assistants to inspect database schemas, execute queries, and perform various database operations with a focus on security and performance monitoring.

Use cases

Use cases for mcp-sql include automating database queries through AI assistants, performing real-time data analysis, generating performance reports, managing bulk data transactions, and ensuring secure database operations in enterprise applications.

How to use

To use mcp-sql, ensure you have Node.js version 18.0.0 or higher installed along with a Microsoft SQL Server database. After installation, you can connect to your database and utilize its features such as schema inspection, query execution, and performance monitoring through the provided API.

Key features

Key features of mcp-sql include full MSSQL support, comprehensive schema inspection, safe query execution with parameterized queries, real-time performance monitoring, SQL injection prevention, efficient batch operations, optimized connection pooling, and native integration with MCP-compatible tools.

Where to use

mcp-sql is suitable for use in various fields that require database management and interaction, particularly in environments where AI assistants are utilized for data analysis, reporting, and operational tasks.

MCP SQL Server

A Model Context Protocol server that provides comprehensive access to SQL
databases, starting with MSSQL support. This server enables AI assistants to
inspect database schemas, execute queries, and perform database operations with
enterprise-grade security and performance monitoring.

Current Status: MSSQL fully supported. MySQL and PostgreSQL support coming
in future releases.

✨ Key Features

• Database Support: Full MSSQL support (MySQL and PostgreSQL coming soon)
• Schema Inspection: Comprehensive database structure analysis and metadata
  extraction
• Query Execution: Safe SQL execution with parameterized queries and result
  formatting
• Performance Monitoring: Real-time metrics, query statistics, and
  performance reports
• Security First: SQL injection prevention, connection encryption, and
  access controls
• Batch Operations: Efficient bulk query execution and transaction
  management
• Connection Pooling: Optimized connection management with configurable pool
  settings
• MCP Integration: Native support for Claude Desktop, Cursor, and other
  MCP-compatible tools

📦 Installation & Setup

Prerequisites

• Node.js 18.0.0+ - Download here
• Database Server: Microsoft SQL Server (MSSQL)
• AI Assistant: Claude Desktop, Cursor, or any MCP-compatible tool

Note: Currently only MSSQL is supported. MySQL and PostgreSQL support will
be added in future releases.

Quick Installation

# Install globally via NPM
npm install -g @donggyunryu/mcp-sql

Basic Configuration

Refer to env.example

Create a .env file with your database settings:

# Create .env file with your database settings
# DB_TYPE=mssql # Current only MSSQL supported
DB_HOST=localhost
DB_PORT=1433
DB_DATABASE=your_database
DB_USER=your_username
DB_PASSWORD=your_password
DB_ENCRYPT=false
DB_TRUST_SERVER_CERTIFICATE=true

Test Connection

# Test your database connection
npm run test:db # in local environment

#or
npx @donggyunryu/mcp-sql test:db

🚀 Quick Start

Local Environment

1. Clone the repository:

   git clone https://github.com/ryudg/mcp-sql.git
   cd mcp-sql
   

2. Install dependencies

   npm install
   

3. Build the project

   npm run build
   

4. Add to your mcp.json or setting.json, claude_desktop_config.json

Configure AI Assistant

For Claude Desktop:

Add to your claude_desktop_config.json:

For Cursor(VSCode, Windsurf… etc IDE):

Add to your MCP settings:

Start Using

Restart your AI assistant and try:

"Show me all tables in my database"
"What's the structure of the users table?"
"Find all active users from the last 30 days"

💬 Usage Examples

Schema Exploration

"Show me all tables in the database"
"What's the structure of the users table?"
"List all columns in the orders table with their data types"

Data Queries

"Find all active users registered in the last 30 days"
"Show me the top 10 customers by total order value"
"Get all pending orders from this month"

Performance Monitoring

"Show me current connection pool status"
"What are the slowest queries in the last hour?"
"Generate a performance report for today"

🛠️ Available Tools

The MCP SQL server provides the following tools for database interaction:

Schema & Discovery Tools

Query Execution Tools

Performance & Monitoring Tools

🛡️ Security

• Connection Encryption: TLS/SSL connection support
• Parameter Binding: SQL injection prevention
• Access Control: Database user permission-based control
• Logging: Complete query execution logging
• Input Validation: Comprehensive input sanitization

Security Best Practices

• Use dedicated database users with minimal required permissions
• Enable SSL/TLS encryption for database connections when possible
• Use connection pooling with appropriate limits
• Never commit credentials to version control
• Use environment variables for all sensitive configuration

🗺️ Roadmap

Upcoming Features

• 🔮 Multi-Database Support

  • MySQL adapter implementation
  • PostgreSQL adapter implementation
  • Unified database interface

• ⚡ Performance & Caching

  • Query result caching system
  • Advanced performance optimization
  • Connection pool enhancements

• 🧪 Testing & Quality

  • Comprehensive test coverage (100%)
  • Automated CI/CD pipeline
  • Performance benchmarking

• 🚀 Advanced Features

  • GraphQL integration support
  • Enhanced monitoring dashboard
  • Plugin architecture for extensibility

• 📊 Analytics & Insights

  • Advanced query analytics
  • Database performance insights
  • Usage statistics and reporting

View CHANGELOG

Support & Community

• 📋 Issues:
  Report bugs or request features
• 💬 Discussions:
  Community discussions and Q&A
• 📖 Documentation:
  Comprehensive guides and API docs

📝 License

This project is licensed under the MIT License. See the LICENSE file
for details.

Made with for the AI-powered development community

MCP SQL Server v1.0.0 - Bridging AI and databases