mcp-server-apache-airflow

Catalog onlyCatalog onlySTDIO

Overview

This project is a Model Context Protocol (MCP) server implementation for Apache Airflow, enabling seamless integration with MCP clients. It provides a standardized way to interact with Apache Airflow through the Model Context Protocol.

To use this project, set the required environment variables for your Airflow instance and configure it in your claude_desktop_config.json or run the server manually using Python.

Standardized API for interacting with Apache Airflow - Support for DAG management, including listing, pausing, and unpausing DAGs - Ability to create and manage DAG runs - Health status and version retrieval

Integrating Apache Airflow with other systems using the Model Context Protocol.
Managing workflows in a standardized manner.
Monitoring and controlling DAGs and their runs programmatically.

Add to your AI client

Use these steps to connect mcp-server-apache-airflow in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "mcp-server-apache-airflow-yangkyeongmo": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-apache-airflow-yangkyeongmo"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "mcp-server-apache-airflow-yangkyeongmo": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-apache-airflow-yangkyeongmo"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "mcp-server-apache-airflow-yangkyeongmo": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-apache-airflow-yangkyeongmo"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "mcp-server-apache-airflow-yangkyeongmo": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-apache-airflow-yangkyeongmo"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp-server-apache-airflow-yangkyeongmo": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-apache-airflow-yangkyeongmo"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "mcp-server-apache-airflow-yangkyeongmo": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-apache-airflow-yangkyeongmo"
      ]
    }
  }
}

FAQ

What is the Model Context Protocol?

The Model Context Protocol is a standard for interacting with data processing systems like Apache Airflow.

How do I set up the server?

Set the required environment variables and configure your client as per the provided instructions.

Can I contribute to this project?

Yes! Contributions are welcome, and you can submit a Pull Request.

Developer tools

mcp-server-apache-airflow — MCP Registry