MCP.so
ログイン

🛠️ dbt MCP Server

@kannandreams

🛠️ dbt MCP Server について

dbt-mcp-server

基本情報

カテゴリ

データと分析

ランタイム

python

トランスポート

stdio

公開者

kannandreams

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "dbt-mcp-server": {
      "command": "docker",
      "args": [
        "build",
        "-t",
        "dbt-mcp-server",
        "."
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is dbt MCP Server?

The dbt MCP Server is a minimal, extensible MCP (Model Context Protocol) server that provides a unified JSON-based interface for running dbt models, tests, and other dbt operations. It can be triggered via CLI, HTTP API, or an AI interface like Claude, and includes Slack notifications for task completions.

How to use dbt MCP Server?

Run the server locally with uvicorn mcp_dispatcher:app --reload --port 8000 or use Docker with docker build -t dbt-mcp-server . then docker run -p 8000:8000 dbt-mcp-server. Trigger dbt models by executing python mcp_dispatcher.py mcp_request.json with a JSON spec. Integrate with Claude via python claude_client_example.py. Set the SLACK_WEBHOOK_URL environment variable to receive Slack alerts.

Key features of dbt MCP Server

  • Run dbt models using a clean JSON spec
  • Accept CLI or HTTP API calls
  • Slack alerts for model success or failure
  • Compatible with AI tools like Claude
  • Extensible and minimal design
  • Unified interface for triggering dbt operations

Use cases of dbt MCP Server

  • Automate dbt model runs by chatting with Claude
  • Trigger dbt tests and models via a REST API
  • Receive immediate Slack notifications on model completion or errors
  • Integrate dbt into AI-driven data pipelines

FAQ from dbt MCP Server

What does this server do compared to other dbt tools?

It provides a minimal, extensible MCP interface to trigger dbt models and tests using a unified JSON spec, making it easy to integrate with AI assistants like Claude.

What are the runtime requirements?

You need Python with uvicorn to run locally, or Docker for containerized deployment. The server runs on port 8000.

How do I get Slack alerts?

Set the SLACK_WEBHOOK_URL environment variable to your Slack webhook URL. Alerts are sent on model success or failure.

How can I use this with Claude?

Run the provided claude_client_example.py script after starting the server. This allows Claude to trigger dbt operations via the MCP interface.

What license does this server use?

It is licensed under the MIT License, allowing free use, modification, and distribution.

コメント

「データと分析」の他のコンテンツ