DBT Semantic Layer MCP server

Integrates with the DBT Semantic Layer API to enable querying and analysis of data models defined in DBT, supporting report generation, ad-hoc analysis, and data-driven application development.
Back to servers
Provider
Tommaso
Release date
Mar 01, 2025
Language
TypeScript
Stats
9 stars

This MCP server acts as a bridge between AI assistants like Claude and the dbt Semantic Layer, allowing you to query metrics, explore definitions, and analyze data through natural language conversations. The server enables you to interact with your dbt metrics directly from your AI assistant interface.

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:

Basic Interactions

  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?
    

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

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

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later