local_pgsql

Database Analytics & Query Automation Toolkit

Core Features

Database Interaction Tools

• Schema Exploration
  • List all tables (list_tables)
  • Get table schema (get_table_schema)
• Data Sampling
  • Preview table contents (get_table_sample)
• Custom Query Execution
  • Run parameterized SQL (run_query)
• Statistical Analysis
  • Numerical summaries (get_summary_statistics: mean, std.dev, etc.)
  • Correlation matrices (analyze_correlations)
  • Group-by aggregations (group_by_analysis: multi-function support)
• Time Series Processing
  • Temporal aggregation (time_series_analysis)
• Anomaly Detection
  • Z-score/IQR based detection (detect_anomalies)

Built-in Prompts Library

• SQL Cheatsheet (basic_sql_guide)
• Analysis Task Templates (data_analysis_tasks)

Technical Architecture

• Modular Design: Dynamic tool registration via @mcp.tool decorator
• Type Safety: Strict input/output typing (e.g., List[Dict], Optional)
• Database Abstraction: DatabaseManager interface for backend-agnostic operations

Use Cases

1. Data Exploration: Rapid dataset understanding
2. Automated Reporting: Scheduled statistical summaries
3. Anomaly Monitoring: Real-time data quality checks
4. AI-Augmented Analysis: Structured data access for LLMs

Integration Example

# Initialize MCP with database
mcp = MCP()
db = DatabaseManager("postgresql://user:pass@localhost/db")
register_tools(mcp, db)
register_prompts(mcp)

# Tool usage examples
tables = mcp.call_tool("list_tables")
stats = mcp.call_tool("get_summary_statistics", {"table_name": "sales"})