Dbt MCP Server

🛠️ dbt Model Control Protocol (MCP) Server

A minimal and extensible MCP (Model Control Protocol) server for running dbt models through a unified interface.

If you like this repository, please give it a ⭐️ — it means a lot!

🚀 Quick Start

✅ Ready to integrate with AI tools like Claude!

Run Locally (Using 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

Use Claude to Trigger MCP (Supported Client)

python claude_client_example.py

📣 Slack Alerts

Set the SLACK_WEBHOOK_URL to receive alerts when models succeed or fail.

🔌 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 specification.
• Support CLI or HTTP API calls.
• Slack alerts for model status.
• Compatibility with AI tools like Claude.

🛠️ Contribution Guidelines

If you're interested in contributing code or ideas, feel free to open an issue for discussion or submit a pull request directly. All contributions, whether they're code, suggestions, or feedback, are welcome!

📄 License

This MCP server is distributed under the MIT License. This means you're free to use, modify, and distribute the software, but you must adhere to the terms and conditions of the MIT License. For more details, please refer to the LICENSE file in the project repository.