MCP server · Developer tools

Apache Airflow MCP server

Lets your AI check and manage your Apache Airflow workflows for you, right from the chat.

Developer tools For it and development Developer Tools

This is a small helper that connects your AI assistant to Apache Airflow, the tool many teams use to schedule and run data jobs. Once it is set up, you can ask your AI questions about your workflows or tell it to make simple changes, instead of clicking around the Airflow website. It is handy for anyone who works with data pipelines but does not want to memorize every menu.

What is an MCP server? The 30-second version

On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI a new skill or a connection to another app. This one connects your AI to Apache Airflow, so it can look up your workflows and, if you allow it, change them for you. You just ask in plain words, and the helper does the talking to Airflow behind the scenes.

What this MCP server does

You ask your AI something about your Airflow setup, like which workflows exist or why a run failed. Your AI passes that request to this helper program running on your computer. The helper then talks to your Airflow server using its official connection method. Airflow sends back the details, and the helper hands them to your AI. Your AI then explains the answer to you in normal language in the chat.

Flow diagram: you ask your AI “Why did my daily_sales workflow fail?”, on your own computer the Apache Airflow MCP server works with apache Airflow, and you get back A plain answer in the chat.

Click to zoom

What you can do with it

List all your workflows (called DAGs) and see their details
Pause or unpause a workflow
Start a new run of a workflow
Check the status of past runs and their tasks
Read the log of a task that failed
Look at variables, connections, and pools
Check the overall health of your Airflow setup

Try asking your AI

“List all my Airflow DAGs and tell me which ones are paused”
“Why did the last run of my daily_sales DAG fail?”
“Show me the log for the extract task in the latest run of my_etl”
“Pause the old_reporting DAG for me”

What it gives back to you

You get answers in plain language in the chat, like a list of workflow names, a summary of a run, or the text of a task log. If you ask it to change something, like pausing a workflow or starting a run, it tells you what it did. Numbers and statuses come back as simple sentences you can read at a glance.

Before you start

What you need

An Apache Airflow server you can reach, with its web address
A username and password for Airflow, or a JWT token (a kind of temporary password)
Python installed on your computer, plus the uv tool if you use the uvx command
The Claude desktop app or another AI app that supports MCP servers

Good to know

This helper can change or delete things in Airflow, like pausing workflows, starting runs, or removing variables, so set READ_ONLY to true if you only want it to look and not touch.

Install it with your AI

Add Apache Airflow MCP server to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check Apache Airflow MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.