$ loading_
Connect to Apache Airflow to inspect workflows, trigger DAGs, and monitor health.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "mcp-airflow" yet — see the docs or source repo.
List recently failed DAGs in Airflow, including DAG name, failure time, and latest run status, sorted by failure time descending.
A list of failed DAGs for quickly identifying problematic workflows.
Trigger a new run for the DAG "daily_etl_job" and return the run ID, trigger time, and current status.
Key details of the new DAG run, confirming the job was successfully started.
Check the health status of the Airflow scheduler and indicate whether it is healthy and if any issues need attention.
The scheduler health check result with a brief explanation of any detected issues.
Manage Apache Airflow workflows with natural language for monitoring, task control, and configuration.
Inspect Airflow DAGs, runs, logs, and trigger or clear workflows.
Expose OpenAPI endpoints as MCP tools for LLM-driven REST API access.
Expose Django REST Framework APIs as secure MCP tools for AI agents.
Expose GraphQL operations as AI-callable tools for integration and automation.
Manage Databricks clusters, jobs, SQL, and catalogs through MCP tools.