Apache Airflow MCP server

Provides a bridge to Apache Airflow for managing and monitoring workflows through natural language, enabling DAG management, task execution, and resource administration without leaving your assistant interface.
Back to servers
Provider
Gyeongmo Yang
Release date
Feb 13, 2025
Language
Python
Package
Stats
11.0K downloads
39 stars

This Apache Airflow MCP server implementation provides a standardized interface for interacting with Apache Airflow through the Model Context Protocol. It wraps Airflow's REST API, allowing MCP clients to manage DAGs, tasks, variables, connections, and more in a consistent way.

Installation

Prerequisites

Before installing, ensure you have access to an Apache Airflow instance with API access.

Environment Setup

Set the following environment variables for authentication:

AIRFLOW_HOST=<your-airflow-host>
AIRFLOW_USERNAME=<your-airflow-username>
AIRFLOW_PASSWORD=<your-airflow-password>
AIRFLOW_API_VERSION=v1  # Optional, defaults to v1

Installation Options

Using Smithery

The easiest way to install the MCP server for Claude Desktop is via Smithery:

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

Usage

Configuration with Claude Desktop

Add the MCP server configuration to your claude_desktop_config.json:

{
  "mcpServers": {
    "mcp-server-apache-airflow": {
      "command": "uvx",
      "args": ["mcp-server-apache-airflow"],
      "env": {
        "AIRFLOW_HOST": "https://your-airflow-host",
        "AIRFLOW_USERNAME": "your-username",
        "AIRFLOW_PASSWORD": "your-password"
      }
    }
  }
}

Alternative Configuration

If you prefer using uv directly:

{
  "mcpServers": {
    "mcp-server-apache-airflow": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/mcp-server-apache-airflow",
        "run",
        "mcp-server-apache-airflow"
      ],
      "env": {
        "AIRFLOW_HOST": "https://your-airflow-host",
        "AIRFLOW_USERNAME": "your-username",
        "AIRFLOW_PASSWORD": "your-password"
      }
    }
  }
}

API Group Selection

You can select specific API groups if you don't need all functionality:

uv run mcp-server-apache-airflow --apis "dag,dagrun"

Available API groups:

  • config
  • connections
  • dag
  • dagrun
  • dagstats
  • dataset
  • eventlog
  • importerror
  • monitoring
  • plugin
  • pool
  • provider
  • taskinstance
  • variable
  • xcom

Manual Execution

Run the server directly with:

make run

Options:

  • --port: Port to listen on for SSE (default: 8000)
  • --transport: Transport type (stdio/sse, default: stdio)

Or run the SSE server specifically:

make run-sse

Supported Features

The MCP server supports a comprehensive set of Apache Airflow API features including:

DAG Management

  • List, view, pause, unpause, update, and delete DAGs
  • Access DAG source code and reparse DAG files

DAG Runs

  • List, create, view, update, and delete DAG runs
  • Clear DAG runs and manage run notes

Task Management

  • List and view DAG tasks
  • Manage task instances
  • Clear task instances and update their states

Variables, Connections, and Pools

  • Full CRUD operations for Airflow variables
  • Connection management and testing
  • Pool management

Additional Features

  • XCom entry management
  • Dataset operations
  • Monitoring and health status
  • Configuration access
  • Plugins and providers listing
  • Event logs and import errors

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later