Vertica MCP Server

A Model Context Protocol (MCP) server that provides comprehensive Vertica Database integration capabilities for AI assistants and agents.

Features

• Query Execution: Execute SQL queries with safety controls (SELECT, DESCRIBE, EXPLAIN only)

• Schema Inspection: Browse database tables, views, and Vertica-specific projections

• Database Documentation: Generate comprehensive database documentation

• Query Analysis: Analyze query performance with execution plans

• Data Export: Export query results in JSON and CSV formats

• Vertica-Specific: Support for projections, cluster status, and columnar storage features

Related MCP server: MCP Toolkit

Installation

Prerequisites

• Python 3.11 or higher

• Access to a Vertica database

• uv package manager

Install from Source

Install as Package

Quick Start

1. Set up environment variables:

   export DB_CONNECTION_STRING="vertica://username:password@hostname:5433/database"

2. Start the MCP server:

   vertica-mcp-server

3. Use with AI assistants that support MCP (like Claude Desktop or VS Code extensions)

Configuration

Connection String Formats

URL Format (recommended):

Simple Format:

When using simple format, set these environment variables:

• VERTICA_USER: Database username

• VERTICA_PASSWORD: Database password

Environment Variables

Docker Development

A Docker setup is provided for testing with Vertica Community Edition:

See docker-example/README.md for detailed instructions.

Available Tools

The MCP server provides these tools for AI assistants:

• execute_query: Execute SQL queries (SELECT, DESCRIBE, EXPLAIN only)

• describe_table: Get detailed table column information

• list_tables: List all tables with metadata

• list_views: List all database views

• list_projections: List Vertica projections (unique to Vertica)

• explain_query: Get query execution plans

• generate_sample_queries: Generate example queries for tables

• export_query_results: Export query results as JSON or CSV

Vertica-Specific Features

This server includes Vertica-specific functionality:

• Projections: List and inspect Vertica projections

• Columnar Storage: Handle Vertica's columnar data types

• Query Optimization: Vertica-specific query execution plans

• Data Types: Support for Vertica data types (UUID, ARRAY, etc.)

Safety Features

• Query Restriction: Only SELECT, DESCRIBE, and EXPLAIN statements allowed

• Row Limiting: Automatic LIMIT clause added to prevent large result sets

• SQL Injection Protection: Basic protection against malicious queries

• Whitelisting: Optional table and column whitelisting

Development

Running Tests

Code Quality

Project Structure

Contributing

1. Fork the repository

2. Create a feature branch

3. Make your changes

4. Add tests for new functionality

5. Run the test suite

6. Submit a pull request

License

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

Changelog

0.1.0

• Initial release

• Core MCP server functionality

• Vertica database integration

• Query execution and schema inspection

• Docker development environment

• Comprehensive test suite