Claude Desktop 및 기타 호환 AI 보조를 통해 dbt Semantic 레이어를 완벽하게 쿼리하는 모델 커넥터 프레서 (MCP) 서버.

dbt Semantic 층은 무엇입니까?

dbt Semantic Layer는 dbt 프로젝트에서 한 번 메트릭을 정의하고 전체 데이터 스택에 걸쳐 지속적으로 재사용 할 수있는 강력한 기능입니다. 그것은 제공합니다:

• 사업 메트릭에 대한 진실의 단일 소스
• 모든 데이터 도구에서 일관된 메트릭 정의
• 모든 팀 구성원을위한 복잡한 메트릭 액세스

이 프로젝트 소개

이 MCP 서버는 AI 조수 (클래드와 같은)와 dbt Semantic 층 사이의 브리지 역할을합니다.

• 자연 언어 대화를 통해 Query 메트릭
• 유효한 메트릭과 정의를 탐구
• 치수 고장 및 필터가있는 분석 데이터
• AI Assistant 인터페이스 내에서 결과를 시각화

특징

• PhysicsMetric Discovery: dbt Semantic Layer에서 검색할 수 있는 메트릭
• Query Creation: 자연적인 언어를 통해 semantic 쿼리 생성 및 실행
• deep 데이터 분석: 필터, 그룹, 그리고 더 깊은 통찰력을 위한 주문 메트릭

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.

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 consistently across your entire data stack. It provides:

• A single source of truth for business metrics
• Consistent metric definitions across all data tools
• Simplified access to complex metrics for all team members

About This Project

This MCP server acts as a bridge between AI assistants (like Claude) and the dbt Semantic Layer, enabling you to:

• Query metrics directly through natural language conversations
• Explore available metrics and their definitions
• Analyze data with dimensional breakdowns and filters
• Visualize results within your AI assistant interface

Features

• 🔍 Metric Discovery: Browse and search available metrics in your dbt Semantic Layer
• 📊 Query Creation: Generate and execute semantic queries through natural language
• 🧮 Data Analysis: Filter, group, and order metrics for deeper insights
• 📈 Result Visualization: Display query results in an easy-to-understand format

Prerequisites

• A dbt Cloud account with Semantic Layer enabled
• API access to your dbt Cloud instance
• Node.js (v14 or later)

Installation

Via Smithery (Recommended)

The easiest way to install is via Smithery:

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

Usage

Once installed and configured, you can interact with the dbt Semantic Layer directly from Claude Desktop:

1. Ask about available metrics: “What metrics are available in my dbt Semantic Layer?”
2. Query specific metrics: “Show me monthly revenue for the last quarter grouped by product category”
3. Analyze trends: “What’s the week-over-week growth in user signups?”

Troubleshooting

If you encounter issues:

• Verify your API credentials are correct
• Ensure your dbt Cloud project has Semantic Layer enabled
• Check that your metrics are properly defined in your dbt project

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgments

• dbt Labs for creating the dbt Semantic Layer
• Smithery for the MCP deployment platform
• LiteMCP for the MCP development package