MCP Airflow API
Monitor and manage Apache Airflow clusters through natural language queries via MCP tools: DAG inspection, task monitoring, health checks, and cluster analytics without API complexity. * Guide: https://call518.medium.com/mcp-airflow-api-a-model-conte
What is MCP Airflow API?
MCP Airflow API is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to monitor and manage apache airflow clusters through natural language queries via mcp tools: dag inspection, task monitoring, health checks, and cluster analytics without api complexity. * guide: https:...
Monitor and manage Apache Airflow clusters through natural language queries via MCP tools: DAG inspection, task monitoring, health checks, and cluster analytics without API complexity. * Guide: https://call518.medium.com/mcp-airflow-api-a-model-conte
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Monitor and manage Apache Airflow clusters through natural l
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mcp-airflow-apiConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use MCP Airflow API
MCP-Airflow-API is an MCP server that exposes 43-45 tools for monitoring and managing Apache Airflow clusters through natural language, covering DAG operations, task instance monitoring, resource management (pools, variables, connections), cluster health checks, and analytics — without requiring users to interact directly with the Airflow REST API. It supports both Airflow 2.x and Airflow 3.0+ API versions, can run via uvx or Docker, and integrates with Claude Desktop or any MCP-compatible client. DevOps engineers and data engineers can use it to inspect, trigger, pause, and debug Airflow workflows conversationally.
Prerequisites
- Python 3.12+ installed (for uvx installation)
- A running Apache Airflow instance with REST API enabled (version 2.x or 3.0+)
- Airflow API credentials (username and password)
- uv package manager installed, OR Docker for container-based setup
- An MCP-compatible client such as Claude Desktop
Install via uvx
Run the server directly from PyPI using uvx with Python 3.12. No clone or pip install needed.
uvx --python 3.12 mcp-airflow-apiSet required environment variables
Configure the Airflow connection details. AIRFLOW_API_VERSION must be v1 for Airflow 2.x or v2 for Airflow 3.0+.
export AIRFLOW_API_VERSION=v2
export AIRFLOW_API_BASE_URL=http://localhost:8080/api
export AIRFLOW_API_USERNAME=airflow
export AIRFLOW_API_PASSWORD=airflowConfigure Claude Desktop
Add the MCP server to your claude_desktop_config.json with the Airflow connection details in the env block.
{
"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"
}
}
}
}Start a full demo environment with Docker Compose
For local testing, use Docker Compose to spin up Airflow, the MCP server, and OpenWebUI together.
git clone https://github.com/call518/MCP-Airflow-API.git
cd MCP-Airflow-API
docker-compose up -dVerify connectivity
Ask your AI assistant to check cluster health to confirm the server is connected to your Airflow instance.
MCP Airflow API Examples
Client configuration
Claude Desktop configuration to connect MCP-Airflow-API to a local Airflow 3.0+ instance via uvx.
{
"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"
}
}
}
}Prompts to try
Natural language queries you can send to your AI assistant to manage and monitor Apache Airflow through the MCP server.
- "List all DAGs in my Airflow cluster"
- "Show me all currently running DAG runs"
- "Trigger the DAG named 'example_complex'"
- "Get the task instance logs for the 'data_processing' DAG"
- "Check the health status of the Airflow cluster"
- "List all Airflow variables"Troubleshooting MCP Airflow API
Connection refused or 401 Unauthorized from Airflow API
Verify AIRFLOW_API_BASE_URL points to a reachable Airflow instance and that the REST API is enabled in your airflow.cfg (api.auth_backend must be set). Double-check AIRFLOW_API_USERNAME and AIRFLOW_API_PASSWORD credentials against your Airflow admin panel.
Tools for assets or data assets return 'not found' or 404 errors
Asset management tools are only available in Airflow 3.0+ API (AIRFLOW_API_VERSION=v2). If you are on Airflow 2.x, set AIRFLOW_API_VERSION=v1 and avoid using asset-specific tools.
uvx fails with Python version error
The package requires Python 3.12. Pass --python 3.12 explicitly to uvx: uvx --python 3.12 mcp-airflow-api. If Python 3.12 is not installed, install it via your system package manager or pyenv.
Frequently Asked Questions about MCP Airflow API
What is MCP Airflow API?
MCP Airflow API is a Model Context Protocol (MCP) server that monitor and manage apache airflow clusters through natural language queries via mcp tools: dag inspection, task monitoring, health checks, and cluster analytics without api complexity. * guide: https://call518.medium.com/mcp-airflow-api-a-model-conte It connects AI assistants to external tools and data sources through a standardized interface.
How do I install MCP Airflow API?
Follow the installation instructions on the MCP Airflow API GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with MCP Airflow API?
MCP Airflow API works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is MCP Airflow API free to use?
Yes, MCP Airflow API is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
MCP Airflow API Alternatives — Similar Cloud Services Servers
Looking for alternatives to MCP Airflow API? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up MCP Airflow API in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use MCP Airflow API?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.