- Home
- MCP servers
- Vertica
Vertica
- python
3
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": {
"nolleh-mcp-vertica": {
"command": "uvx",
"args": [
"mcp-vertica"
],
"env": {
"VERTICA_SSL": "false",
"VERTICA_HOST": "localhost",
"VERTICA_PORT": "5433",
"VERTICA_USER": "dbadmin",
"VERTICA_DATABASE": "VMart",
"VERTICA_PASSWORD": "test_password",
"VERTICA_CONNECTION_LIMIT": "10",
"VERTICA_SSL_REJECT_UNAUTHORIZED": "true"
}
}
}
}You can run an MCP (Model Context Protocol) Vertica server to connect your MCP clients to a Vertica database. This server handles database connections, executes queries, streams results, and manages schema and security permissions in a scalable way. Use the provided MCP configurations to run Vertica either through UVX or via Docker, and tailor the connection details to your Vertica setup.
How to use
Configure your MCP client to connect to the Vertica MCP server using one of the standard methods shown below. You can run the server through UVX (a local, in-process approach) or via Docker (containerized). Each method includes the necessary environment variables to establish the Vertica connection. After configuring, you can start issuing SQL queries, stream large results in batches, load data with COPY, and manage tables, indexes, views, and constraints through the server’s capabilities.
To begin, create or edit your MCP client settings and add one of the following connection configurations under mcpServers. The entries below show the exact shape you can copy into your client config.
How to install
Prerequisites: make sure you have Node.js and npm installed, or your preferred runtime that can execute MCP commands. You will also need Docker if you choose the containerized option.
Option 1: Install via UVX (local process) 1. Ensure UVX is installed on your system. 2. Add the Vertica MCP server entry to your MCP client config as shown in the UVX example below. 3. Start your MCP client and verify the Vertica connection.
Option 2: Run via Docker (containerized) 1. Ensure Docker is installed and running. 2. Add the Vertica MCP server entry to your MCP client config as shown in the Docker example below. 3. Start your MCP client and verify the Vertica connection.
Configuration and examples
You can adapt environment variables to point to your Vertica instance. The following example shows the required environment values for a typical local Vertica setup.
{
"mcpServers": {
"vertica": {
"command": "uvx",
"args": ["mcp-vertica"],
"env": {
"VERTICA_HOST": "localhost",
"VERTICA_PORT": 5433,
"VERTICA_DATABASE": "VMart",
"VERTICA_USER": "dbadmin",
"VERTICA_PASSWORD": "test_password",
"VERTICA_CONNECTION_LIMIT": 10,
"VERTICA_SSL": false,
"VERTICA_SSL_REJECT_UNAUTHORIZED": true
}
}
}
}
If you prefer passing arguments explicitly, you can expand the command line arguments as shown in this alternative configuration.
{
"mcpServers": {
"vertica": {
"command": "uvx",
"args": [
"mcp-vertica",
"--host=localhost",
"--db-port=5433",
"--database=VMart",
"--user=dbadmin",
"--password=test_password",
"--connection-limit=10"
]
}
}
}
For Docker, use this configuration to run the Vertica MCP server in a container and supply the same Vertica connection details via environment variables.
{
"mcpServers": {
"vertica": {
"command": "docker",
"args": ["run", "-i", "--rm", "nolleh/mcp-vertica"],
"env": {
"VERTICA_HOST": "localhost",
"VERTICA_PORT": 5433,
"VERTICA_DATABASE": "VMart",
"VERTICA_USER": "dbadmin",
"VERTICA_PASSWORD": "test_password",
"VERTICA_CONNECTION_LIMIT": 10,
"VERTICA_SSL": false,
"VERTICA_SSL_REJECT_UNAUTHORIZED": true
}
}
}
}
Security and notes
Boolean flags like SSL can be enabled by including the flag in the command line arguments. If a password is not required, you can use an empty string as shown in the examples.
Appendix: Development and testing
Debug mode helps you troubleshoot by increasing verbosity when running the server in Docker. Use the DEBUG environment variable to control log levels.
# Run with maximum verbosity
docker run -e DEBUG=3 -e VERTICA_HOST=localhost ... nolleh/mcp-vertica:latest
# Run with medium verbosity
docker run -e DEBUG=2 -e VERTICA_HOST=localhost ... nolleh/mcp-vertica:latest
# Pass additional arguments
docker run -e EXTRA_ARGS="--connection-limit=20" -e VERTICA_HOST=localhost ... nolleh/mcp-vertica:latest
You can also set these variables in a docker-compose.yml file to keep the configuration portable.
Appendix: VerticaDB Docker Compose example shows a ready-to-use setup that wires Vertica with the MCP server for quick testing.
Available tools
execute_query
Execute SQL queries against Vertica and return results.
stream_query
Stream large query results in batches with configurable batch size.
copy_data
Load data efficiently using the COPY command.
get_table_structure
Inspect table structure including columns, constraints, and details.
list_indexes
List all indexes for a table with type and uniqueness.
list_views
List all views in a schema along with definitions.