dbt Semantic Layer MCP Server

What is dbt Semantic Layer MCP Server?

The dbt Semantic Layer MCP Server is a Model Context Protocol server that enables querying the dbt Semantic Layer through AI assistants like Claude Desktop. It acts as a bridge to explore, query, and visualize dbt metrics using natural language, providing a single source of truth for business metrics.

How to use dbt Semantic Layer MCP Server?

Install via Smithery (recommended) using the command npx -y @smithery/cli install @TommyBez/dbt-semantic-layer-mcp --client claude. You need a dbt Cloud account with Semantic Layer enabled and API access, plus Node.js v14 or later. After configuration, ask natural language questions about metrics from Claude Desktop.

Key features of dbt Semantic Layer MCP Server

• Browse and search available metrics in your dbt Semantic Layer
• Generate and execute semantic queries through natural language
• Filter, group, and order metrics for deeper analysis
• Display query results in an easy-to-understand format
• Work with any compatible AI assistant interface

Use cases of dbt Semantic Layer MCP Server

• Ask "What metrics are available in my dbt Semantic Layer?" to discover metrics
• Query monthly revenue for the last quarter grouped by product category
• Analyze week-over-week growth in user signups with natural language
• Explore metric definitions with dimensional breakdowns and filters

FAQ from dbt Semantic Layer MCP Server

What prerequisites are needed to use this server?

You need a dbt Cloud account with Semantic Layer enabled, API access to your dbt Cloud instance, and Node.js v14 or later.

How do I install the dbt Semantic Layer MCP Server?

The recommended installation method is via Smithery using the command npx -y @smithery/cli install @TommyBez/dbt-semantic-layer-mcp --client claude.

How can I troubleshoot issues with queries?

Verify that your API credentials are correct, ensure your dbt Cloud project has Semantic Layer enabled, and check that your metrics are properly defined in your dbt project.

Can I use this server with AI assistants other than Claude Desktop?

Yes, the server is described as compatible with Claude Desktop and other compatible AI assistants.

What types of queries can I make with natural language?

You can ask about available metrics, query specific metrics with filters and groupings (e.g., time periods, product categories), and analyze trends like week-over-week growth.