This project provides an MCP (Model Context Protocol) server for interacting with dbt, enabling seamless integration of dbt functionalities into various IDEs and AI coding assistants. It targets developers and data engineers who leverage dbt for data transformation and want to enhance their workflow with intelligent tooling.

How It Works

The server acts as a bridge, exposing dbt's core commands (build, compile, docs, ls, parse, run, test, show) and Semantic Layer capabilities (list_metrics, get_dimensions, get_entities, query_metrics) via the MCP. It also supports Discovery API functions for model introspection and Remote capabilities for natural language to SQL generation and execution. Configuration is managed through environment variables, allowing customization for dbt Cloud instances, multi-cell setups, and specific tool group enablement.

Quick Start & Requirements

• Install: Copy .env.example to .env and configure environment variables.
• Prerequisites: A dbt project, dbt Cloud access token (with specific permissions for Semantic Layer), and potentially dbt CLI/Fusion executables.
• Integration: Configuration snippets are provided for MCP clients like Claude Desktop, Cursor, and VS Code.

Highlighted Details

• Exposes dbt CLI commands for model lifecycle management.
• Provides access to dbt Semantic Layer metrics and entities.
• Enables model discovery and introspection.
• Supports natural language to SQL generation and execution via Remote tools.

Maintenance & Community

This project is from dbt-labs, the creators of dbt. Contribution instructions are available in CONTRIBUTING.md.

Licensing & Compatibility

The repository does not explicitly state a license in the provided README. Users should verify licensing for commercial use or closed-source integration.

Limitations & Caveats

The README does not specify a license, which may impact commercial adoption. Users must ensure their dbt Cloud service token has the necessary permissions for Semantic Layer and Metadata operations.