SQL MCP Server
Enables AI models to interact with multiple database types (MySQL, MSSQL, Oracle, Sybase) through a unified interface with standardized tools for querying, inspecting schemas, and managing connections without requiring separate server configurations.
README
SQL MCP Server
The SQL MCP Server is a unified agentic interface that allows AI models (like Claude) to inspect, query, and interact with multiple types of databases through a single, standardized set of tools.
Instead of installing and configuring separate servers for MySQL, SQL Server, Oracle, etc., this single package handles them all by dynamically loading the correct "adapter" based on your configuration.
🚀 Features
- Standardized Toolset: The AI always sees the same tools (
execute_query,describe_table,get_db_version), no matter if it's talking to Oracle or MySQL. This reduces hallucinations and improves query accuracy. - Resources: Automatically exposes database tables as MCP Resources for easy inspection.
- Smart Adapters:
- ✅ MySQL: Uses
mysql-connector-pythonwith connection pooling. - ✅ MSSQL: Uses
pymssqland auto-detects schema names (e.g.,dbo.Users). - ✅ Sybase / SAP IQ: Uses
pyodbcand intelligently handlesdba.prefixes and server names. - ✅ Oracle: Uses
oracledb(Thin mode) for easy connectivity without complex driver installs.
- ✅ MySQL: Uses
- Unicode Ready: All connections default to UTF-8 to handle special characters seamlessly.
🛠️ Installation
-
Clone the repository:
git clone https://github.com/BryR0/sql-mcp.git cd sql-mcp -
Create a virtual environment:
python -m venv venv source venv/bin/activate # On Windows: .\venv\Scripts\activate -
Install dependencies:
pip install -e .
⚙️ Configuration
You define which database to use via the DB_TYPE environment variable.
Supported Environment Variables
| Variable | Description | Required | Default |
|---|---|---|---|
DB_TYPE |
Type of DB: mysql, mssql, sybase, oracle |
Yes | mysql |
DB_HOST |
Hostname or IP address | Yes | localhost |
DB_USER |
Database username | Yes | root |
DB_PASSWORD |
Database password | Yes | (empty) |
DB_DATABASE |
Database name | Yes | test |
DB_PORT |
Port number | No | Auto (3306, 1433, etc.) |
DB_DSN |
Connection string (Oracle/Sybase advanced) | No | (empty) |
DB_SERVER_NAME |
Explicit Server Name (Sybase only) | No | (empty) |
Claude Desktop Config Example
Add this to your claude_desktop_config.json. Note that DB_PORT is optional and will default to the standard port for the chosen DB type if omitted.
{
"mcpServers": {
"sql_mcp_mysql": {
"command": "C:\\path\\to\\venv\\python.exe",
"args": ["-m", "sql_mcp"],
"env": {
"DB_TYPE": "mysql",
"DB_HOST": "localhost",
"DB_USER": "root",
"DB_PASSWORD": "password",
"DB_DATABASE": "my_db"
}
},
"sql_mcp_mssql": {
"command": "C:\\path\\to\\venv\\python.exe",
"args": ["-m", "sql_mcp"],
"env": {
"DB_TYPE": "mssql",
"DB_HOST": "192.168.1.50",
"DB_USER": "sa",
"DB_PASSWORD": "password",
"DB_DATABASE": "DataWarehouse"
}
}
}
}
🏗️ Architecture
The project uses an Adapter Pattern:
- Server receives a request (e.g.,
execute_query). - Factory checks
DB_TYPEand instantiates the correct class (e.g.,MSSQLAdapter). - Adapter translates the generic request into specific driver calls (
pymssql,pyodbc, etc.). - Response is formatted back to a standard JSON structure for the AI.
This means you can switch databases just by changing the config, without changing the AI's prompts or logic.
📄 License
This project is licensed under the MIT License. See the LICENSE file for details.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.