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. It exposes 74 tools across 8 categories.

Features

Diagnose Tools (12)

Performance diagnosis and analysis tools.

Tool	Description
diagnose_realtime	Real-time database performance diagnosis
diagnose_sql	SQL statement analysis with execution plan
diagnose_slow_queries	Slow query analysis
diagnose_table	Table-level diagnosis
diagnose_bottleneck	Performance bottleneck analysis
diagnose_space	Tablespace usage analysis
diagnose_connections	Connection analysis
diagnose_replication	Replication status analysis
diagnose_bloat	Table bloat and fragmentation analysis
diagnose_index_usage	Index usage analysis
diagnose_vacuum	Vacuum requirements analysis
diagnose_indexes	Index recommendations

Monitor Tools (9)

Health monitoring and capacity planning.

Tool	Description
monitor_health	Database health checks
monitor_metrics	Performance metrics collection
monitor_anomalies	Anomaly detection
monitor_capacity	Capacity prediction
monitor_trend	Trend analysis
monitor_history	Historical metric data
monitor_alerts	Alert retrieval
monitor_baseline	Baseline comparison
monitor_degradation	Performance degradation detection

SQL Tools (9)

SQL execution and data management.

Tool	Description
sql_execute	Execute SQL statements
sql_rewrite	SQL optimization and rewriting
sql_batch	Batch SQL execution
sql_export	Export data to CSV/JSON/SQL
sql_import	Import data from file
sql_audit	SQL execution audit records
sql_quality	SQL quality analysis
sql_schema	Table schema information
sql_tables	List all tables

Security Tools (12)

Security auditing and compliance.

Tool	Description
security_sql_injection	SQL injection detection
security_score	Database security scoring
security_sensitive_data	Sensitive data scanning
security_permissions	Permission auditing
security_config	Configuration auditing
security_audit	Comprehensive security audit
security_password_policy	Password policy checking
security_weak_passwords	Weak password detection
security_login	Login security checking
security_high_risk	High risk operation detection
security_compliance	Compliance checking
security_audit_log	Audit log analysis

Inspector Tools (8)

Intelligent inspection and analysis.

Tool	Description
inspector_inspect	Comprehensive inspection
inspector_intelligent	AI-powered intelligent inspection
inspector_anomalies	Anomaly detection
inspector_root_cause	Root cause analysis
inspector_risks	Risk prediction
inspector_baseline_create	Performance baseline creation
inspector_baseline_compare	Baseline comparison
inspector_top_issues	Top issues retrieval

Lock Analyzer Tools (6)

Lock analysis and deadlock detection.

Tool	Description
lock_analyze	Current lock analysis
lock_deadlocks	Deadlock detection
lock_chains	Lock wait chain tracing
lock_statistics	Lock statistics
lock_report	Lock analysis report
lock_kill_transaction	Blocking transaction termination

Scheduler Tools (10)

Backup, scheduling, and task management.

Tool	Description
scheduler_backup	Database backup
scheduler_list_backups	List available backups
scheduler_restore	Backup restoration
scheduler_schedule_task	Task scheduling
scheduler_list_tasks	List scheduled tasks
scheduler_run_now	Immediate task execution
scheduler_dlq	Dead letter queue tasks
scheduler_dlq_retry	DLQ task retry
scheduler_task_logs	Task execution logs
scheduler_status	Scheduler status

Auditor Tools (8)

SQL audit and quality analysis.

Tool	Description
auditor_audit_sql	SQL statement auditing
auditor_ddl_impact	DDL impact analysis
auditor_optimize	SQL optimization
auditor_indexes	Index recommendations
auditor_explain	Execution plan analysis
auditor_cost	Cost estimation
auditor_rules	Audit rules listing
auditor_report	Audit report generation

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"
• "Show me the top 10 slow queries"
• "Execute this SQL: SELECT COUNT(*) FROM orders"
• "Run a comprehensive security audit"
• "Detect any deadlocks in my database"
• "List all scheduled tasks and their status"
• "Predict my disk space usage for the next 30 days"

Development

Prerequisites

• Python 3.10+
• dbskiter >= 2.1.0

Building from Source

# Clone the repository
git clone https://github.com/magicCzc/dbskiter-mcp-server.git
cd dbskiter-mcp-server

# Install development dependencies
pip install -e ".[dev]"

# Run tests
pytest tests/

# Build package
python -m build

License

MIT License

Author

MagiCzc - magiczc@139.com