DBT CLI Model Context Protocol Server

Overview

The DBT CLI Model Context Protocol (MCP) Server is a specialized server that wraps the dbt CLI tool, enabling AI coding agents to interact with dbt projects through standardized MCP tools. This implementation allows for seamless integration of dbt operations within AI-driven workflows.

Features

• 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

Installation

Prerequisites

• Python 3.10 or higher
• uv tool for Python environment management
• dbt CLI installed

Setup

# Clone the repository with submodules
git clone --recurse-submodules https://github.com/yourusername/dbt-cli-mcp.git
cd dbt-cli-mcp

# If you already cloned without --recurse-submodules, initialize the submodule
# git submodule update --init

# Create and activate a virtual environment
uv venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

# Install dependencies
uv pip install -e .

# For development, install development dependencies
uv pip install -e ".[dev]"

Usage

Command Line Interface

The package provides a command-line interface for direct interaction with dbt:

# Run dbt models
dbt-mcp run --models customers --project-dir /path/to/project

# Run dbt models with a custom profiles directory
dbt-mcp run --models customers --project-dir /path/to/project --profiles-dir /path/to/profiles

# List dbt resources
dbt-mcp ls --resource-type model --output-format json

# Run dbt tests
dbt-mcp test --project-dir /path/to/project

# Get help
dbt-mcp --help
dbt-mcp run --help

You can also use the module directly:

python -m src.cli run --models customers --project-dir /path/to/project

Command Line Options

• --dbt-path: Path to dbt executable (default: "dbt")
• --env-file: Path to environment file (default: ".env")
• --log-level: Logging level (default: "INFO")
• --profiles-dir: Path to directory containing profiles.yml file (defaults to project-dir if not specified)

Environment Variables

The server can also be configured using environment variables:

• DBT_PATH: Path to dbt executable
• ENV_FILE: Path to environment file
• LOG_LEVEL: Logging level
• DBT_PROFILES_DIR: Path to directory containing profiles.yml file

Using with MCP Clients

To use the server with an MCP client like Claude for Desktop, add it to the client's configuration:

{
  "mcpServers": {
    "dbt": {
      "command": "uv",
      "args": ["--directory", "/path/to/dbt-cli-mcp", "run", "src/server.py"],
      "env": {
        "DBT_PATH": "/absolute/path/to/dbt",
        "ENV_FILE": ".env"
        // You can also set DBT_PROFILES_DIR here for a server-wide default
      }
    }
  }
}

Available Tools

The server provides the following MCP tools:

• dbt_run: Run dbt models
• dbt_test: Run dbt tests
• dbt_ls: List dbt resources
• dbt_compile: Compile dbt models
• dbt_debug: Debug dbt project setup
• dbt_deps: Install dbt package dependencies
• dbt_seed: Load CSV files as seed data
• dbt_show: Preview model results

dbt Profiles Configuration

When using the dbt MCP tools, it's important to understand how dbt profiles are handled:

1. The project_dir parameter must point to a directory that contains both:
2. A valid dbt_project.yml file
3. A valid profiles.yml file with the profile referenced in the project
4. The MCP server automatically sets the DBT_PROFILES_DIR environment variable to the absolute path of the directory specified in project_dir. This tells dbt where to look for the profiles.yml file.
5. If you encounter a "Could not find profile named 'X'" error, it means either:
6. The profiles.yml file is missing from the project directory
7. The profiles.yml file doesn't contain the profile referenced in dbt_project.yml

Example of a valid profiles.yml file:

jaffle_shop:  # This name must match the profile in dbt_project.yml
  target: dev
  outputs:
    dev:
      type: duckdb
      path: 'jaffle_shop.duckdb'
      threads: 24

When running commands through the MCP server, ensure your project directory is structured correctly with both configuration files present.

Development

Integration Tests

The project includes integration tests that verify functionality against a real dbt project:

# Run all integration tests
python integration_tests/run_all.py

# Run a specific integration test
python integration_tests/test_dbt_run.py

Test Project Setup

The integration tests use the jaffle_shop_duckdb project which is included as a Git submodule in the dbt_integration_tests directory. When you clone the repository with --recurse-submodules as mentioned in the Setup section, this will automatically be initialized.

If you need to update the test project to the latest version from the original repository:

git submodule update --remote dbt_integration_tests/jaffle_shop_duckdb

If you're seeing errors about missing files in the jaffle_shop_duckdb directory, you may need to initialize the submodule:

git submodule update --init

License

MIT