$ loading_
Let AI inspect and operate Airflow DAGs, runs, tasks, and logs.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "Airflow MCP" yet — see the docs or source repo.
Use Airflow MCP to check the last three runs of the DAG named daily_etl and summarize whether any failed.
Returns the last three DAG run results and a brief summary of any failures.
Use Airflow MCP to find the failed task instances in the most recent failed run of sales_pipeline and review the key log details.
Lists failed task instances and highlights log details useful for troubleshooting.
Use Airflow MCP to trigger the report_refresh DAG, then keep checking the status of that DAG run and its task instances.
Triggers the specified DAG and returns progress updates for the run and task states.
DevOps engineers or developers can have AI directly inspect DAGs and DAG runs to quickly understand whether scheduled workflows are healthy. It fits routine monitoring and anomaly detection.
When an Airflow task fails, users can use this tool to let AI inspect task instances and logs, reducing troubleshooting time. It is useful for data pipeline or batch job incidents.
When teams need to operate on DAGs, this MCP server exposes the Airflow REST API to AI agents. That enables inspection and operational workflows directly in a conversation.
It is a Model Context Protocol server that exposes Apache Airflow's REST API to AI agents. This allows AI to inspect and operate on DAGs, DAG runs, task instances, and logs.
Based on the description, it can work with DAGs, DAG runs, task instances, and logs. The provided information does not mention support for other objects.
The provided material does not include installation steps or prerequisites. See the source repository for the exact setup.
Connect to Apache Airflow to inspect workflows, trigger DAGs, and monitor health.
Monitor Airflow DAG status, recent runs, history, and performance metrics read-only.
Inspect Airflow DAGs, runs, logs, and trigger or clear workflows.
Manage Akiflow tasks, projects, and calendar with AI agents.
Build AI agent workflows and automate tasks using MCP-connected services.
Monitor, manage, and debug Prefect workflows and resources through AI.