MCP server · Developer tools

Airflow MCP server

Let your AI check Airflow workflows, see what failed, and start a run for you.

Developer tools For it and development For operations Data Platforms

This is a small helper that connects your AI assistant to Apache Airflow, the tool many teams use to schedule and run their data jobs. Once it is set up, you can ask your AI plain questions about your workflows instead of clicking around the Airflow website. It is handy for anyone who keeps an eye on scheduled jobs, even if you are not the person who built them.

What is an MCP server? The 30-second version

On its own, your AI can only chat. 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 your own Airflow setup, so it can look up your workflows and start runs when you ask. You set it up once, and after that your AI can talk to Airflow for you.

What this MCP server does

You ask your AI something about your Airflow jobs, like which ones failed today. The AI passes that request to this helper program. The helper talks to your Airflow server using its normal web address, logging in with the username and password you gave it. Airflow sends back the details, and the helper hands them to your AI. Your AI then explains the answer to you in the chat, in normal words.

Flow diagram: you ask your AI “Which Airflow workflows failed today?”, the Airflow MCP server connects it to Airflow, and you get back answer in chat.

Click to zoom

What you can do with it

List all your workflows and see which are paused or active
See all the runs that happened today and how each one ended
Check the latest status of one specific workflow
Start a workflow run by hand
Look at the individual steps inside a run
Find workflows that failed in the last 24 hours
Check whether the Airflow scheduler is alive and healthy

Try asking your AI

“Which Airflow workflows failed in the last 24 hours?”
“Show me all the DAG runs from today and their status.”
“What is the latest run status for the daily sales DAG?”
“Is the Airflow scheduler healthy right now?”
“Trigger a run of the daily sales DAG.”

What it gives back to you

You get answers in the chat, not files. Usually that means a list of workflow names with their status, or a short summary of what ran today and what failed. If you ask about one workflow, you get its latest run status and the steps inside that run. If you trigger a run, the AI tells you whether Airflow accepted it.

Before you start

What you need

An Apache Airflow server you can reach, with its web address
A username and password for that Airflow server
Python and the uvx or pip tool to run the package
An MCP client like the Claude desktop app, set up to use this server

Good to know

It can start workflow runs, so be careful with the trigger command, and it uses your Airflow username and password, so keep those private.

Install it with your AI

Add 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 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.