MCP-Airflow-API is a Model Context Protocol server that enables natural language management of Apache Airflow clusters. It transforms complex Airflow REST API operations into intuitive conversational commands, allowing you to monitor, control, and troubleshoot workflows without writing manual API calls. Key features of MCP-Airflow-API: - Full DAG lifecycle management including listing, triggering, pausing, and monitoring workflow runs - Deep visibility into task logs, source code browsing, and execution history for troubleshooting - Configuration management for Airflow variables, connection strings, and resource pools - Cluster health monitoring with quick views of failed tasks, event logs, and run durations - Cross-version compatibility supporting both Airflow 2.x (API v1) and Airflow 3.x+ (API v2) clusters - Asset management capabilities for data-aware scheduling workflows in Airflow 3.x environments

🚀 MCP-Airflow-API

> Revolutionary Open Source Tool for Managing Apache Airflow with Natural Language

[](https://opensource.org/licenses/MIT)

[](https://smithery.ai/server/@call518/mcp-airflow-api) [](https://www.buymeacoffee.com/call518)

[](https://github.com/call518/MCP-Airflow-API/actions/workflows/pypi-publish.yml)

---

Architecture & Internal (DeepWiki)

[](https://deepwiki.com/call518/MCP-Airflow-API)

---

📋 Overview

Have you ever wondered how amazing it would be if you could manage your Apache Airflow workflows using natural language instead of complex REST API calls or web interface manipulations? MCP-Airflow-API is the revolutionary open-source project that makes this goal a reality.

---

🎯 What is MCP-Airflow-API?

MCP-Airflow-API is an MCP server that leverages the Model Context Protocol (MCP) to transform Apache Airflow REST API operations into natural language tools. This project hides the complexity of API structures and enables intuitive management of Airflow clusters through natural language commands.

🆕 Multi-Version API Support (NEW!)

Now supports both Airflow API v1 (2.x) and v2 (3.0+) with dynamic version selection via environment variable:

Key Architecture: Single MCP server with shared common tools (43) plus v2-exclusive asset tools (2) - dynamically loads appropriate toolset based on AIRFLOW_API_VERSION environment variable!

Traditional approach (example):

curl -X GET "http://localhost:8080/api/v1/dags?limit=100&offset=0" \
  -H "Authorization: Basic YWlyZmxvdzphaXJmbG93"

MCP-Airflow-API approach (natural language): > "Show me the currently running DAGs"

---

🚀 Quickstart

> 📝 Need a test Airflow cluster? Use our companion project Airflow-Docker-Compose with support for both Airflow 2.x and Airflow 3.x environments!

Flow Diagram of Quickstart/Tutorial

🎯 Recommended: Docker Compose (Complete Demo Environment)

For quick evaluation and testing:

git clone https://github.com/call518/MCP-Airflow-API.git
cd MCP-Airflow-API
Configure your Airflow credentials
cp .env.example .env
Edit .env with your Airflow API settings
Start all services
docker-compose up -d
Access OpenWebUI at http://localhost:3002/
API documentation at http://localhost:8002/docs

Getting Started with OpenWebUI (Docker Option)

> 📌 Note: Web-UI configuration instructions are based on OpenWebUI v0.6.22. Menu locations and settings may differ in newer versions.

1. Access http://localhost:3002/ 2. Log in with admin account 3. Go to "Settings" → "Tools" from the top menu 4. Add Tool URL: http://localhost:8002/airflow-api 5. Configure your LLM provider (Ollama, OpenAI, etc.)

---

📦 MCP Server Installation Methods

Method 1: Direct Installation from PyPI

uvx --python 3.12 mcp-airflow-api

Method 2: Claude-Desktop MCP Client Integration

Local Access (stdio mode)

{
  "mcpServers": {
    "mcp-airflow-api": {
      "command": "uvx",
      "args": ["--python", "3.12", "mcp-airflow-api"],
      "env": {
        "AIRFLOW_API_VERSION": "v2",
        "AIRFLOW_API_BASE_URL": "http://localhost:8080/api",
        "AIRFLOW_API_USERNAME": "airflow",
        "AIRFLOW_API_PASSWORD": "airflow"
      }
    }
  }
}git

Remote Access (streamable-http mode without authentication)

{
  "mcpServers": {
    "mcp-airflow-api": {
      "type": "streamable-http",
      "url": "http://localhost:8000/mcp"
    }
  }
}

Remote Access (streamable-http mode with Bearer token authentication - Recommended)

```json { "mcpServers": { "mcp-airflow-api": { "type": "streamable-http",