Skip to main content

MCP Server for DBSKiter - Database monitoring, diagnosis, and SQL processing

Project description

DBSKiter MCP Server

A Model Context Protocol (MCP) server that exposes DBSKiter database skills to AI assistants.

Overview

DBSKiter MCP Server provides AI assistants with powerful database monitoring, diagnosis, SQL optimization, and security auditing capabilities through the Model Context Protocol.

Features

Diagnose Tools

  • diagnose_realtime - Real-time database performance diagnosis
  • diagnose_sql - SQL statement analysis with execution plan
  • diagnose_slow_queries - Slow query analysis

Monitor Tools

  • monitor_health - Database health checks
  • monitor_metrics - Performance metrics collection

SQL Tools

  • sql_execute - Execute SQL statements
  • sql_rewrite - SQL optimization and rewriting

Security Tools

  • security_sql_injection - SQL injection detection
  • security_score - Database security scoring

Installation

pip install dbskiter-mcp-server

Configuration

Environment Variables

Create a .env file with your database connections:

# MySQL Example
DB_DIALECT=mysql
DB_HOST=localhost
DB_PORT=3306
DB_USER=root
DB_PASSWORD=your_password
DB_NAME=your_database

# Oracle Example
ORACLE_DIALECT=oracle+oracledb
ORACLE_HOST=localhost
ORACLE_PORT=1521
ORACLE_USER=system
ORACLE_PASSWORD=your_password
ORACLE_SERVICE_NAME=ORCL

Claude Desktop Configuration

Add to your Claude Desktop configuration (claude_desktop_config.json):

{
  "mcpServers": {
    "dbskiter": {
      "command": "dbskiter-mcp",
      "env": {
        "DB_DIALECT": "mysql",
        "DB_HOST": "localhost",
        "DB_PORT": "3306",
        "DB_USER": "root",
        "DB_PASSWORD": "your_password",
        "DB_NAME": "your_database"
      }
    }
  }
}

Usage

Running the Server

# Run directly
dbskiter-mcp

# Or with Python
python -m dbskiter_mcp

Using with Claude

Once configured, you can ask Claude to:

  • "Check the health of my database"
  • "Analyze this slow SQL query: SELECT * FROM users WHERE name LIKE '%test%'"
  • "Show me the top 10 slow queries"
  • "Execute this SQL: SELECT COUNT(*) FROM orders"

Development

Setup

git clone https://github.com/magicCzc/dbskiter-mcp-server.git
cd dbskiter-mcp-server
pip install -e ".[dev]"

Testing

pytest

Code Formatting

black src/

Architecture

dbskiter_mcp/
├── __init__.py          # Package initialization
├── server.py            # MCP server implementation
└── tools.py             # Tool definitions and handlers

The server uses the official MCP Python SDK and follows the Model Context Protocol specification.

Requirements

  • Python 3.10+
  • dbskiter >= 2.0.0
  • mcp >= 1.0.0

License

MIT License - see LICENSE file for details.

Contributing

Contributions are welcome! Please submit issues and pull requests on GitHub.

Support

For issues and questions:

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

dbskiter_mcp_server-1.0.1.tar.gz (12.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

dbskiter_mcp_server-1.0.1-py3-none-any.whl (9.5 kB view details)

Uploaded Python 3

File details

Details for the file dbskiter_mcp_server-1.0.1.tar.gz.

File metadata

  • Download URL: dbskiter_mcp_server-1.0.1.tar.gz
  • Upload date:
  • Size: 12.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.8

File hashes

Hashes for dbskiter_mcp_server-1.0.1.tar.gz
Algorithm Hash digest
SHA256 2d006acae5b18b59afe43e63372cb02c3862703662492dc0d86f1310640f6ad0
MD5 e15884017de8bd7e961936b7964ff5a7
BLAKE2b-256 6196594f0d5a678e6d2fd2526378f77e8887a224fa57083896276057bfeeedff

See more details on using hashes here.

File details

Details for the file dbskiter_mcp_server-1.0.1-py3-none-any.whl.

File metadata

File hashes

Hashes for dbskiter_mcp_server-1.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 61e2ab076a4f084e45735f8052e833813343f720bf280bd169086e08195c4984
MD5 23d4215c99462ae394920ecf7c2d81e4
BLAKE2b-256 0c314379ad362cfe4450fa7719d3ef6531800a6e8b3f6be8ae5e642ffa16ac83

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page