MCP Database Utilities for AI Data Analysis

Overview

MCP Database Utilities is a versatile MCP service that enables your AI to perform data analysis by securely accessing various types of databases (SQLite, MySQL, PostgreSQL, etc.) through a unified configuration. It acts as a secure bridge between AI systems and databases, allowing AI to read and analyze data without direct database access or the risk of data modification.

Key Features

• Multi-Database Support: Connect to SQLite, MySQL, PostgreSQL, and more.
• Secure Architecture: Strictly read-only operations, isolated connections, and automatic timeouts.
• Local Processing: All data processing occurs locally, ensuring no data is sent to external servers.
• Simple Configuration: Manage all database connections using a single YAML file.
• Advanced Tools: Table browsing, schema analysis, and query execution.

Security and Privacy

Data Protection

• Strictly Read-Only: Only SELECT queries are allowed.
• Isolated Connections: Each database connection is managed and isolated separately.
• Automatic Timeouts: Long-running operations are automatically terminated to prevent resource abuse.

Privacy Assurance

• Local Processing: All data is processed locally, with no data sent to external servers.
• Credential Protection: Connection credentials are never exposed to AI models.
• Sensitive Data Masking: Passwords and connection details are automatically hidden in logs.

Enterprise-Level Security

• SSL/TLS Support: Encrypted connections to remote databases.
• Configuration Separation: YAML configuration files eliminate interpretation risks.
• User-Controlled Access: You decide which databases can be accessed.

System Requirements

• Python: 3.10 or higher.
• Database Support:
• SQLite 3.x
• PostgreSQL 12+
• MySQL 8+
• AI Clients:
• Claude Desktop
• Cursor
• Any MCP-compatible client

Getting Started

Installation Guide

Option A: Using uvx (Recommended)

1. Install uv and uvx:
   shell curl -LsSf https://astral.sh/uv/install.sh | sh
2. Create a configuration file (config.yaml) with your database connection details.
3. Add the configuration to your AI client:
   json "dbutils": { "command": "uvx", "args": ["mcp-dbutils", "--config", "/path/to/your/config.yaml"] }

Option B: Using Docker

1. Install Docker from docker.com.
2. Create a configuration file (config.yaml).
3. Add the configuration to your AI client:
   json "dbutils": { "command": "docker", "args": ["run", "-i", "--rm", "-v", "/path/to/your/config.yaml:/app/config.yaml", "mcp/dbutils", "--config", "/app/config.yaml"] }

Option C: Using Smithery (Claude One-Click Configuration)

npx -y @smithery/cli install @donghao1393/mcp-dbutils --client claude

Usage

Once installed and configured, your AI can:
- List tables in the database.
- View table structures.
- Execute SQL queries securely.
- Analyze data across multiple databases.

Example Interaction:
- You: "Can you list all the tables in my database?"
- AI: "Here are the tables in your database: customers, products, orders, inventory, employees."

Available Tools

• dbutils-list-tables: List all tables in the database.
• dbutils-run-query: Execute SQL queries (SELECT only).
• dbutils-get-stats: Get statistics about tables.
• dbutils-list-constraints: List table constraints.
• dbutils-explain-query: Get query execution plans.
• dbutils-get-performance: Get database performance metrics.
• dbutils-analyze-query: Analyze queries for optimization.

Need More Help?

• Technical Documentation
• GitHub Issues
• Smithery

License

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