# Apache Airflow (Bearer Token)

> Use this tool when you need to manage Apache Airflow workflows programmatically with secure Bearer token authentication. It solves problems such as automating DAG operations, task instance management, and connection handling for data engineers and teams, providing a comprehensive interface to the Airflow REST API. Ideal for integrating Airflow operations into AI workflows, especially in cloud deployments requiring secure token-based authentication.

Canonical page: https://skillsregistry.net/skills/nikhil-ganage-airflow-token  
JSON: https://api.skillsregistry.net/v1/skills/nikhil-ganage-airflow-token

## Description

This MCP server provides AI assistants with comprehensive Apache Airflow management capabilities through Bearer token authentication, built by Nikhil Ganage as a fork of Gyeongmo Yang's original implementation with enhanced token-based security support. The implementation exposes the full Airflow REST API including DAG operations (listing, triggering, pausing), task instance management, connection handling, variable management, dataset operations, and monitoring functions, with optional read-only mode for safe querying and automatic UI link generation for enhanced workflow visibility. Serves data engineers needing AI-powered Airflow administration, teams requiring programmatic DAG management through conversational interfaces, and organizations wanting to integrate Airflow operations into their AI workflows with secure token-based authentication for cloud deployments like Astronomer.

## Trust

- **Trust score (0–1):** 0.99
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** devops-ci
- **Updated:** 2026-09-19

## Source

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

## 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": "nikhil-ganage-airflow-token"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/nikhil-ganage-airflow-token` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/nikhil-ganage-airflow-token/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