MCP Vertica

What is MCP Vertica?

MCP Vertica is a Model Context Protocol (MCP) server that provides a standardized interface for AI assistants to interact with a Vertica database. It is designed for developers and data analysts who want to query, manage, and load data into Vertica using natural language or MCP-compatible clients.

How to use MCP Vertica?

Install via Smithery (npx -y @smithery/cli install @nolleh/mcp-vertica --client claude) or manually configure your MCP client’s settings file with either uvx or Docker. Set environment variables for connection details (e.g., VERTICA_HOST, VERTICA_PORT, VERTICA_DATABASE, VERTICA_USER, VERTICA_PASSWORD) or pass them as command-line arguments. Optionally configure operation permissions and schema-level permissions using environment variables.

Key features of MCP Vertica

• Connection pooling with configurable limits
• SSL/TLS support and automatic connection cleanup
• Execute SQL queries and stream large results in batches
• Bulk data loading via COPY command
• Table structure inspection, index and view management
• Operation-level and schema-specific permissions

Use cases of MCP Vertica

• Querying Vertica databases using natural language through an AI assistant
• Streaming large query results in batches for efficient processing
• Bulk loading large datasets into Vertica tables
• Inspecting database schemas, indexes, and views
• Managing database permissions at the operation and schema level

FAQ from MCP Vertica

What is MCP Vertica?

MCP Vertica is the first implementation of a Vertica MCP server, enabling AI tools to interact with Vertica databases via the Model Context Protocol.

What are the runtime requirements?

MCP Vertica requires Python (uvx), or can be run as a Docker container. A Vertica database instance must be accessible.

Where does my data live?

All data remains in the Vertica database; the server only acts as a bridge, executing queries and returning results.

What transport modes are supported?

The server supports both stdio (default) and HTTP transport. HTTP transport can be configured via the TRANSPORT and PORT environment variables.

How do I restrict write operations?

Set environment variables like ALLOW_INSERT_OPERATION=false, ALLOW_UPDATE_OPERATION=false, ALLOW_DELETE_OPERATION=false, ALLOW_DDL_OPERATION=false. Schema-specific permissions can be set via SCHEMA_*_PERMISSIONS variables.