yangkyeongmo@/mcp-server-apache-airflow

Overview

An MCP server that connects to Apache Airflow using its official Python client. It exposes Airflow operations as MCP tools, enabling AI agents to interact with Airflow instances programmatically.

Best for

Best for
Developers who want to control Apache Airflow through MCP-compatible AI agents

Use cases

• Trigger and monitor DAG runs from an AI assistant
• List and inspect Airflow DAGs and task instances
• Pause or unpause DAGs via natural language commands

How to use

Install

npx -y @smithery/cli install @yangkyeongmo/mcp-server-apache-airflow --client claude

Tested with

Claude Desktop

Notes

An MCP server that connects to Apache Airflow using its official Python client. It exposes Airflow operations as MCP tools, enabling AI agents to interact with Airflow instances programmatically.

166 stars on GitHub. Last updated 2026-03-03. Licensed MIT.

Use cases

• Trigger and monitor DAG runs from an AI assistant
• List and inspect Airflow DAGs and task instances
• Pause or unpause DAGs via natural language commands

Pros

• Leverages the official Airflow client for reliable connectivity
• Simple setup for developers already using MCP
• Open source with 166 GitHub stars indicating community interest

Cons

• Requires a running Airflow instance with network access
• Limited to operations exposed by the Airflow client API
• Python-only, may not fit non-Python MCP environments

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.