# Apache Airflow

> Use this tool when you need to manage and monitor workflows through natural language, enabling seamless interaction with Apache Airflow for tasks like triggering DAG runs and checking execution status. It solves problems for data engineers and workflow administrators by providing a bridge between AI assistants and Airflow, allowing them to access DAG management, task instances, and monitoring capabilities. With inputs like natural language commands and outputs like structured text content, use Apache Airflow when you want to streamline workflow management without leaving your AI assistant interface.

Canonical page: https://skillsregistry.net/skills/yangkyeongmo-apache-airflow  
JSON: https://api.skillsregistry.net/v1/skills/yangkyeongmo-apache-airflow

## Description

MCP-Server-Apache-Airflow provides a bridge between AI assistants and Apache Airflow, enabling management and monitoring of workflows through natural language. Developed by Gyeongmo Yang, this Python-based server exposes a comprehensive set of Airflow API endpoints including DAG management, task instances, variables, connections, and monitoring capabilities. The implementation supports both stdio and SSE transport modes, authenticates with Airflow via username/password, and returns responses as structured text content. This server is particularly valuable for data engineers and workflow administrators who need to trigger DAG runs, check execution status, or manage Airflow resources without leaving their AI assistant interface.

## Trust

- **Trust score (0–1):** 0.65
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** monitoring
- **Updated:** 2026-09-01

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/yangkyeongmo-apache-airflow)
- **Repository:** <https://github.com/yangkyeongmo/mcp-server-apache-airflow>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "yangkyeongmo-apache-airflow"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/yangkyeongmo-apache-airflow` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/yangkyeongmo-apache-airflow/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt