Airflow Mcp Server

Overview

Airflow Mcp Server is a Model Context Protocol server that connects Apache Airflow to any MCP-compatible AI assistant. Once installed, your AI can call Airflow tools directly within conversations and agent workflows, letting the model decide when to trigger Airflow operations.

The server runs locally as a Python package installed via uvx airflow-mcp-server. It communicates over stdio and requires two environment variables to connect: AIRFLOW_BASE_URL and AUTH_TOKEN for API key authentication. The latest release is v0.9.0 under the MIT license, maintained at abhishekbhakat/airflow-mcp-server on GitHub with 33 stars.

Airflow Mcp Server appears in the AI & Agents category on mcp.site and works with all major MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and Zed. If you maintain this server for abhishekbhakat, claim your listing here to verify ownership, receive the Verified badge, and keep information up to date.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "airflow_mcp_server": {
      "command": "uvx",
      "args": [
        "airflow-mcp-server"
      ],
      "env": {
        "AIRFLOW_BASE_URL": "<airflow-base-url>",
        "AUTH_TOKEN": "<auth-token>"
      }
    }
  }
}

Requires AIRFLOW_BASE_URL, AUTH_TOKEN