AirTrack

Name: AirTrack
Author: Rakesh-infosrc

@Rakesh-infosrc

リポジトリ

AirTrack について

Integrate mcp-server-airflow to Open Web UI

#mcp #airflow #openwebui

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

Rakesh-infosrc

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-airflow-openwebui": {
      "command": "python",
      "args": [
        "-m",
        "venv",
        ".venv"
      ]
    }
  }
}

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 AirTrack?

AirTrack is a Model Context Protocol (MCP) server for Apache Airflow that enables standardized access to DAG metadata, run status, and task insights. It wraps Airflow’s REST API using the official Apache Airflow client library, allowing MCP clients to monitor and automate Airflow workflows in a consistent way.

How to use AirTrack?

Run Airflow with Docker Compose (navigate to airflow directory, run docker-compose up, access at http://localhost:8181 with username admin and password airflow). Then set up the MCP application in the mpc directory: create a Python virtual environment, install dependencies from requirements.txt, and start the server with python server.py. For integration with Claude Desktop, configure the mcpServers JSON with the path to server.py. For Open WebUI, install mcpo using pip, create a config.json with the server path, and run uvx mcpo --config config.json --port 8001.

Key features of AirTrack

Wraps Apache Airflow’s REST API for MCP clients.
Provides DAG metadata, run status, and task insights.
Uses the official Airflow client library for compatibility.
Supports integration with Claude Desktop and Open WebUI.
Runs on Docker Compose and Python 3.8+.
Includes an AirTrack logo image in the MCP folder.

Use cases of AirTrack

Monitor DAG status and task execution from MCP‑capable assistants.
Automate Airflow workflow checks and alerts via MCP clients.
Integrate Airflow observability into chat‑based developer tools.
Enable LLM‑powered troubleshooting of Airflow pipelines (future).

FAQ from AirTrack

What prerequisites are needed to run AirTrack?

Docker and Docker Compose for Airflow, Python 3.8+, and a Python virtual environment for the MCP server.

How do I start the Airflow service?

Navigate to the airflow directory, run docker-compose up, and access the web UI at http://localhost:8181 (login: admin / airflow).

How can I connect AirTrack to Claude Desktop?

Add a JSON entry to the mcpServers configuration in Claude Desktop, specifying the command and path to server.py as shown in the README example.

How do I use AirTrack with Open WebUI?

Install mcpo (pip install mcpo), create a config.json with the server path, then run uvx mcpo --config config.json --port 8001.

What future enhancements are planned for AirTrack?

Planned features include live DAG/task status streaming via WebSocket/SSE, OAuth2 and role‑based security, event‑triggered agents, performance dashboards, and AI‑powered troubleshooting using LLMs.

「データと分析」の他のコンテンツ

HubSpot MCP Server

peakmojo

A Model Context Protocol (MCP) server that enables AI assistants to interact with HubSpot CRM data, providing built-in vector storage and caching mechanisms help overcome HubSpot API limitations while improving response times.

128