Overview
What is mcp-server-apache-airflow?
mcp-server-apache-airflow is a Model Context Protocol (MCP) server implementation that wraps Apache Airflow’s REST API using the official Airflow client library. It enables MCP clients to interact with Airflow in a standardized way.
How to use mcp-server-apache-airflow?
The package is available on PyPI and can be installed via pip. Once configured with an Airflow instance, MCP clients can invoke any of the supported Airflow API operations directly through the MCP protocol.
Key features of mcp-server-apache-airflow
- List, pause, unpause, update, and delete DAGs
- Create, list, update, and delete DAG runs
- Manage tasks and task instances with logging
- CRUD operations for variables, connections, and pools
- Access XComs, datasets, event logs, and health stats
Use cases of mcp-server-apache-airflow
- Automate DAG lifecycle management from MCP-powered assistants
- Monitor and trigger Airflow workflows without manual API calls
- Integrate Airflow operations into broader MCP-based automation pipelines
FAQ from mcp-server-apache-airflow
What does this MCP server allow me to do?
It provides over 50 Airflow REST API operations through the MCP protocol, covering DAGs, runs, tasks, variables, connections, pools, XComs, datasets, monitoring, config, plugins, providers, and event logs.
What dependencies does it require?
It requires a running Apache Airflow instance with its REST API accessible, and uses the official Apache Airflow client library for compatibility.
Does it support authentication with Airflow?
The README does not specify authentication details; users should refer to the Airflow REST API documentation for auth configurations.
