DBT CLI MCP Server logo

DBT CLI MCP Server

by MammothGrowth

A Model Context Protocol (MCP) server that wraps the dbt CLI tool, enabling AI coding agents to interact with dbt projects through standardized MCP tools. It allows execution of dbt commands through MCP tools, supporting major dbt operations.

View on GitHub

Last updated: N/A

What is DBT CLI MCP Server?

The DBT CLI MCP Server is a wrapper around the dbt CLI tool that exposes its functionality through the Model Context Protocol (MCP). This allows AI coding agents to interact with dbt projects in a standardized way.

How to use DBT CLI MCP Server?

To use the server, you need to install it following the provided instructions, configure the necessary environment variables (like DBT_PATH and DBT_PROFILES_DIR), and then use the provided command-line interface or integrate it with an MCP client like Claude for Desktop. Ensure you use absolute paths for the project directory.

Key features of DBT CLI MCP Server

  • Execute dbt commands through MCP tools

  • Support for all major dbt operations (run, test, compile, etc.)

  • Command-line interface for direct interaction

  • Environment variable management for dbt projects

  • Configurable dbt executable path

  • Flexible profiles.yml location configuration

Use cases of DBT CLI MCP Server

  • Integrating dbt projects with AI coding assistants

  • Automating dbt workflows through MCP

  • Standardizing dbt interactions for different tools

  • Enabling programmatic access to dbt functionality

FAQ from DBT CLI MCP Server

What is MCP?

MCP stands for Model Context Protocol, a standard for interacting with data models.

What dbt commands are supported?

The server supports all major dbt operations, including run, test, compile, debug, deps, seed, show, and ls.

How do I configure the dbt executable path?

You can configure the path using the --dbt-path command-line option or the DBT_PATH environment variable.

Why do I need to use absolute paths for the project directory?

The server requires absolute paths to correctly locate the dbt project and profiles.yml file.

How do I resolve 'Could not find profile named 'X'' error?

Ensure the profiles.yml file exists in the project directory, contains the correct profile name, and that you're using an absolute path for project_dir.