DBT Semantic Layer

🚀 dbt Semantic Layer MCP Server

A Model-Connector-Presenter (MCP) server for seamlessly querying the dbt semantic layer through Claude Desktop and other compatible AI assistants.

🚀 Quick Start

This MCP server serves as a bridge between AI assistants (such as Claude) and the dbt semantic layer, enabling you to interact with the dbt semantic layer directly from Claude Desktop after installation and configuration:

1. Inquire about available metrics: "What available metrics are there in my dbt semantic layer?"
2. Query specific metrics: "Show the monthly revenue by product category for the last quarter."
3. Analyze trends: "What is the week-on-week growth of user registrations?"

✨ Features

• 🔍 Metric Discovery: Browse and search for available metrics in the dbt semantic layer.
• 📊 Query Creation: Generate and execute semantic queries via natural language.
• 🧮 Data Calculation: Filter, group, and sort metrics for deeper insights.
• 📈 Result Visualization: Display query results in an easy-to-understand format.

📦 Installation

Via Smithery (Recommended)

The easiest way is to install via Smithery:

npx -y @smithery/cli install @TommyBez/dbt-semantic-layer-mcp --client claude

📚 Documentation

What is the dbt Semantic Layer?

The dbt semantic layer is a powerful feature that allows you to define metrics once in your dbt project and reuse them across your entire data stack. It provides:

• A single source of truth for metric definitions.
• Consistent metric definitions across data tools.
• An easy way to simplify complex metrics for all team members to use.

About This Project

This MCP server acts as a bridge between AI assistants (such as Claude) and the dbt semantic layer, enabling you to:

• Query metrics directly through natural language conversations.
• Browse and search for available metrics and their definitions.
• Conduct data analysis through filtering, grouping, and sorting.
• Visualize results in your AI assistant interface.

🔧 Technical Details

Prerequisites

• A dbt Cloud account with the semantic layer enabled.
• API access to your dbt Cloud instance.
• Node.js (v14 or higher).

Troubleshooting

When encountering issues:

• Verify that your API credentials are correct.
• Ensure that the semantic layer is enabled in your dbt Cloud project.
• Check that your metrics are correctly defined in your dbt project.

📄 License

This project is released under the MIT License. See the LICENSE file for details.

Acknowledgments

• dbt Labs created the dbt semantic layer.
• Smithery provides the MCP deployment platform.
• LiteMCP is the MCP development package.