Jewei MSSQL MCP Server

Project Overview

This is an MCP server developed based on the FastMCP framework, specifically designed for executing data queries and table structure queries on Microsoft SQL Server. The server provides a series of tools that enable clients to conveniently interact with SQL Server databases.

Features

• Data Query: Execute SQL queries and return result sets
• Table Structure Query: Obtain structural information about database tables
• Ease of Use: Provides standardized interfaces through the MCP protocol
• Efficiency and Reliability: Optimized database connection management

Technical Architecture

This project is built using the following technologies:

• FastMCP: A Python framework for building MCP servers
• Python: The primary development language
• Microsoft SQL Server: The target database system
• MCP Protocol: Used for communication between clients and the server

MCP Configuration

This project supports configuring the MCP server through various clients, allowing integration with different IDEs or tools. Below are some configuration examples for common clients:

Windsurf / Cursor / Claude

For clients based on the Windsurf framework (such as Cursor and Claude), you can configure the MCP server in the ~/.codeium/windsurf/mcp_config.json file. Here is an example configuration:

json
{
"mcpServers": {
"jewei-mssql": {
"disabled": false,
"command": "uvx",
"args": [
"jewei-mssql-mcp-server"
],
"env": {
"DB_HOST": "your_db_host",
"DB_USER": "your_db_user",
"DB_PASSWORD": "your_db_password",
"DB_NAME": "your_db_name",
"DB_PORT": "your_db_port"
}
}
}
}

Replace your_db_host, your_db_user, your_db_password, and your_db_name with your actual database connection information.

Cline

For the Cline client, you can add a similar MCP server configuration in its configuration file. Please refer to the official Cline documentation for specific configuration methods. Typically, you need to specify the server name, command, arguments, and environment variables.

json
// Example Cline configuration file (refer to Cline documentation for exact format)
{
"mcpServers": {
"jewei-mssql": {
"command": "uvx",
"args": [
"jewei-mssql-mcp-server"
],
"env": {
"DB_HOST": "your_db_host",
"DB_USER": "your_db_user",
"DB_PASSWORD": "your_db_password",
"DB_NAME": "your_db_name",
"DB_PORT": "your_db_port"
}
}
}
}

Replace the placeholders in the example with your actual database connection information and adjust according to the specific configuration format of Cline.

Installation and Configuration

Prerequisites

• Python 3.7+
• Access to Microsoft SQL Server
• FastMCP library

Installation Steps

Method One: Install via PyPI (Recommended)

bash
pip install jewei-mssql-mcp-server

Method Two: Install from Source Code

1. Clone this repository
   bash
   git clone [Repository URL]
   cd jewei-mssql-mcp-server

2. Install dependencies
   bash
   pip install -r requirements.txt

3. Configure database connection

   • Create a configuration file or set environment variables (see below for specific configuration methods)

Usage

Start the Server

bash
python server.py

By default, the server uses the STDIO transport mechanism. To use HTTP transport, modify the relevant configuration in server.py.

Client Call Example

Any client that supports the MCP protocol can connect to this server. Here is a basic call example:

python
from fastmcp import Client

Connect to the MCP server

client = Client("http://localhost:9000")

Execute SQL query

result = client.call("query_sql", sql="SELECT * FROM users LIMIT 10")
print(result)

Get table structure

structure = client.call("get_table_structure", table_name="users")
print(structure)

Configuration Options

Server configurations can be set in the following ways:

1. Environment Variables
2. Configuration Files
3. Directly in the Code
4. Through uv for MCP server configuration

Using uv to Install and Manage Dependencies

This project supports using uv (a fast Python package manager) to install and manage dependencies. Using uv can significantly improve package installation speed and ensure environment consistency.

First, install uv:

bash

Install uv

pip install uvThen use uv to create a virtual environment and install the dependencies:

bash

Create a virtual environment

uv venv

Activate the virtual environment

Windows

.venvScriptsactivate

Linux/macOS

source .venv/bin/activate

Install dependencies using uv

uv pip install -r requirements.txt

After installation, you can start the MCP server as follows:

bash
python server.py

You can also configure the server in the ~/.codeium/windsurf/mcp_config.json file for integration with Cascade. This project supports using the uvx command to configure the MCP server:

json
{
"mcpServers": {
"jewei-mssql": {
"disabled": false,
"command": "uvx",
"args": [
"jewei-mssql-mcp-server"
],
"env": {
"DB_HOST": "your_db_host",
"DB_USER": "your_db_user",
"DB_PASSWORD": "your_db_password",
"DB_NAME": "your_db_name"
}
}
}
}

Here, uvx is the command used to run the installed Python package, and jewei-mssql-mcp-server is the package name. This method ensures that the MCP server runs in the correct environment.

Main Configuration Items

The main configuration items include:

• Database connection information (server address, username, password, database name)
• Server listening address and port
• Log level

Contribution Guidelines

We welcome code contributions or suggestions for improvement! Please follow these steps:

1. Fork this repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add some amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

License

[Specify license type]

Contact

If you have any questions or suggestions, please contact [contact information].