MCP MS SQL Server
An MCP server for executing queries on a Microsoft SQL Server database.
mcp-mssql-server
A Model Context Protocol (MCP) server that provides a standardized interface for AI models to interact with MS SQL Server databases. This server implements the MCP specification to enable seamless database operations through a consistent API.
Features
- Execute SQL queries with parameter support
- List all tables in the database
- Describe table schemas
- Support for both stdio and HTTP transport modes
- Comprehensive logging system
- Environment-based configuration
- Error handling and graceful shutdown
Prerequisites
- Node.js (version that supports ES modules)
- MS SQL Server instance
- Access credentials for the database
Installation
- Clone the repository
- Install dependencies:
npm install
You can also install the package globally:
npm install -g mcp-mssql-server
- Create a
.envfile in the project root with the following required variables:
DB_SERVER=your_server_address
DB_USER=your_username
DB_PASSWORD=your_password
DB_DATABASE_NAME=your_database_name
Usage
The server can be started in two different transport modes:
stdio Mode (Default)
npm start
# or
npm run start:stdio
HTTP Mode
npm run start:http
Development Mode
npm run dev
JSON-RPC Protocol
The server implements the JSON-RPC 2.0 protocol with the following key methods:
initialize- Initialize the server connection:
{
"jsonrpc": "2.0",
"id": 1,
"method": "initialize",
"params": {
"protocolVersion": "2024-11-05",
"capabilities": {
"tools": {}
},
"clientInfo": {
"name": "your-client",
"version": "1.0.0"
}
}
}
tools/list- List available toolstools/call- Call a specific tool
Testing
The package includes a test client (test.package.js) that demonstrates how to interact with the MCP server:
node test.package.js
The test client implements an MCPTestClient class that:
- Spawns a server process using
npx mcp-mssql-server - Initializes the connection with protocol version '2024-11-05'
- Lists available tools
- Executes sample queries including:
- Listing all tables
- Running a specific SQL query to count documents
- Handles server responses and errors through stdio streams
- Includes proper error handling and process cleanup
Example test query from the client:
{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "execute_sql_query",
"arguments": {
"query": "SELECT COUNT(*) as document_count FROM document_new"
}
}
}
The test client provides a simple way to verify the server's functionality and can serve as a reference for implementing your own client.
Available Tools
The server provides the following MCP tools:
1. execute_sql_query
Execute SQL queries against the database with optional parameterization.
{
"query": "SELECT * FROM Users WHERE id = @userId",
"parameters": [
{
"name": "userId",
"type": "int",
"value": 1
}
]
}
2. list_tables
List all available tables in the connected database.
3. describe_table
Get detailed schema information for a specific table.
{
"table_name": "Users"
}
Logging
Logs are stored in the logs directory:
error.log: Error-level logscombined.log: All logs
In HTTP mode, logs are also output to the console.
Dependencies
Main dependencies:
- @modelcontextprotocol/sdk: ^1.13.0
- dotenv: ^16.4.5
- express: ^5.1.0
- mssql: ^11.0.1
- winston: ^3.11.0
Development dependencies:
- axios: ^1.10.0
License
MIT
Contributing
- Fork the repository
- Create your feature branch
- Commit your changes
- Push to the branch
- Create a new Pull Request
Serveurs connexes
Blockscout
Access blockchain data like balances, tokens, and NFTs from Blockscout APIs. Supports multi-chain and progress notifications.
Kollektiv MCP
Build and access a personal LLM knowledge base from your editor or client without any infrastructure setup.
FRED Economic Data
Access economic data from the Federal Reserve Bank of St. Louis (FRED).
Airtable
Interact with Airtable's API to manage bases, tables, and records.
Airtable
Read and write access to Airtable databases.
Redshift Utils MCP Server
Perform database actions on Amazon Redshift via its Data API.
Supavec MCP Server
Fetch relevant content from Supavec, a vector database service.
MongoDB
Interact with MongoDB databases using natural language. Query collections, inspect schemas, and manage data.
OrionBelt Analytics
Analyzes relational database schemas (PostgreSQL, Snowflake, and Dremio) and automatically generates comprehensive ontologies in RDF/Turtle format with direct SQL mappings.
Right Reasons
Structured business ontology giving AI agents deterministic access to institutional reasoning — 18 MCP tools, Dolt backend, 0% → 100% "why?" recall vs Markdown+RAG.