mcp-dagster: A Dagster MCP Server

Name: mcp-dagster: A Dagster MCP Server
Author: kyryl-opens-ml

@kyryl-opens-ml

リポジトリ

mcp-dagster: A Dagster MCP Server について

概要はまだありません

#mcp-server #dagster #data-orchestration

基本情報

カテゴリ

その他

ライセンス

Apache-2.0

ランタイム

python

トランスポート

stdio

公開者

kyryl-opens-ml

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": {
    "mcp-server-dagster": {
      "command": "uv",
      "args": [
        "run",
        "dagster",
        "dev",
        "-f",
        "./examples/open-ai-agent/pipeline.py"
      ]
    }
  }
}

ツール

Lists all available Dagster repositories

Lists all jobs in a specific repository

Lists all assets in a specific repository

Gets recent Dagster runs (default limit: 10)

Gets detailed information about a specific run

Launches a Dagster job run

Materializes a specific Dagster asset

Terminates an in-progress Dagster run

Gets detailed information about a specific asset

概要

What is mcp-dagster?

mcp-dagster is a Model Context Protocol server that enables AI agents to interact with Dagster, the data orchestration platform. It bridges LLMs and data engineering workflows by allowing agents to explore pipelines, monitor runs, and manage assets.

How to use mcp-dagster?

Install the server from PyPI (mcp-server-dagster) and run it with uv. Start a Dagster instance with your pipeline, then launch the MCP server using SSE transport (uv run examples/open-ai-agent/run_sse_mcp.py). Finally, start the agent loop with uv run ./examples/open-ai-agent/agent.py. The server connects to http://localhost:3000/graphql by default.