What is Dbt Mcp Server

dbt-mcp-server is a minimal and extensible Model Control Protocol (MCP) server designed to execute dbt models through a unified interface, supporting various triggers such as CLI, API, or AI interfaces like Claude.

Use cases

Use cases include automating dbt model runs triggered by events, integrating with CI/CD pipelines, sending alerts for model execution status, and facilitating prompt-driven automation through AI interfaces.

How to use

To use dbt-mcp-server, you can run it locally using UVicorn or deploy it with Docker. You can trigger operations via command line or by sending JSON requests to the server. Additionally, integration with AI tools like Claude is supported for automation.

Key features

Key features include the ability to run dbt models using a clean JSON specification, support for CLI and HTTP API calls, Slack notifications for model success or failure, and compatibility with AI tools like Claude.

Where to use

dbt-mcp-server can be used in data engineering, analytics, and machine learning workflows where dbt models need to be executed and monitored efficiently.

🛠️ dbt MCP Server

This is a minimal, extensible MCP (Model Control Protocol) server to run dbt models with a unified interface.

If you like this repo, leave a ⭐️ — it means a lot!

Overview

A unified JSON-based workflow for triggering dbt models, tests, and other dbt operations, triggered via CLI, API, or an AI interface like Claude. Includes Slack notifications for task completions.

🚀 Getting Started

✅ Ready to plug into AI tools like Claude for prompt-driven automation!

Run Locally with UV

uvicorn mcp_dispatcher:app --reload --port 8000

Run with Docker

docker build -t dbt-mcp-server .
docker run -p 8000:8000 dbt-mcp-server

5. Trigger MCP from Claude (supported client)

python claude_client_example.py

📣 Slack Alerts

Set your SLACK_WEBHOOK_URL to get alerts on model success or failure.

🔌 Usage

python mcp_dispatcher.py mcp_request.json

{
  "mcpServers": {
    "fetch": {
      "command": "node",
      "args": [
        "{ABSOLUTE PATH TO FILE HERE}/dist/index.js"
      ]
    }
  }
}

Features

• Run dbt models using a clean JSON spec
• Accept CLI or HTTP API calls
• Slack alerts for model status
• Compatible with Claude

🛠️ Contributing

If you’re interested in contributing, feel free to open an issue to start a discussion or directly submit a pull request. Whether it’s code, ideas, or feedback—all contributions are welcome!

License

This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.