Vertica

Vertica Database MCP Server

python

1

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "smith-nathanh-vertica-mcp-server": {
      "command": "vertica-mcp-server",
      "args": [],
      "env": {
        "VERTICA_USER": "dbadmin",
        "VERTICA_PASSWORD": "strongpassword",
        "DB_CONNECTION_STRING": "vertica://username:password@hostname:5433/database"
      }
    }
  }
}

You have a dedicated MCP server that integrates Vertica databases with AI assistants. It lets you execute safe, constrained SQL queries, inspect schemas, export data, and analyze performance, all through a consistent MCP interface your AI tools can call.

How to use

To use the Vertica MCP Server with an MCP-capable assistant, first ensure you have a Vertica database you can reach and the required runtime and package manager installed. You will run the MCP server locally and then connect your AI assistant to it using the MCP interface the server exposes.

How to install

Prerequisites you must have before installing: Python 3.11 or higher, access to a Vertica database, and the uv package manager.

Option A — Install from source

git clone <repository-url>
cd vertica-mcp-server
uv sync

Option B — Install as a package

uv add vertica-mcp-server

Optional steps you may perform after installation: set up environment variables, start the server, and verify it is reachable from your MCP client.

Quick start details

Set up the database connection string in your environment to point at your Vertica instance.

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

Start the MCP server so your MCP clients can connect to it.

vertica-mcp-server

Available tools

execute_query

Run SQL queries with safety limits (only SELECT, DESCRIBE, EXPLAIN) to retrieve data from Vertica.

describe_table

Fetch detailed information about table columns, data types, and constraints.

list_tables

List all tables with metadata such as schema, name, and size.

list_views

List all database views with their definitions.

list_projections

List Vertica projections and their properties.

explain_query

Return the execution plan for a given query to analyze performance.

generate_sample_queries

Provide example queries for common tables to help users get started.

export_query_results

Export query results in JSON or CSV formats for downstream use.