Apache Airflow MCP server

The Apache Airflow MCP Server is a standardized interface that wraps Apache Airflow's REST API, allowing Model Context Protocol (MCP) clients to interact with Airflow through a consistent protocol. It leverages the official Apache Airflow client library to provide access to Airflow's capabilities.

Installation

Prerequisites

Before installing the MCP server, ensure you have:

• Python installed (compatible with 3.10, 3.11, and 3.12)
• Access to an Apache Airflow instance

Setting Up the Environment

Set the following environment variables for authentication:

export AIRFLOW_HOST=<your-airflow-host>        # Optional, defaults to http://localhost:8080
export AIRFLOW_USERNAME=<your-airflow-username>
export AIRFLOW_PASSWORD=<your-airflow-password>
export AIRFLOW_API_VERSION=v1                  # Optional, defaults to v1

Installation Options

You can install the MCP server using one of these methods:

Via pip (using uv)

uvx mcp-server-apache-airflow

Via Smithery (for Claude Desktop)

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

Usage

Basic Configuration with Claude Desktop

Add this 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"
      }
    }
  }
}

Running in Read-Only Mode

For enhanced safety (recommended):

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

Alternative Configuration with uv

{
  "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"
      }
    }
  }
}

Selecting Specific API Groups

You can limit which API groups are exposed:

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

To run the server manually:

make run

Options:

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

Or run the SSE server directly:

make run-sse

Read-Only Mode

For security, you can run in read-only mode to prevent write operations:

uv run mcp-server-apache-airflow --read-only

This allows only operations like:

• Listing and viewing resources
• Reading configurations and monitoring data
• Testing connections (non-destructive)

You can combine read-only mode with API selection:

uv run mcp-server-apache-airflow --read-only --apis "dag,variable"

Supported Features

The MCP server supports extensive Airflow functionality, including:

DAG Management

• List, view, pause/unpause, update, and delete DAGs
• View DAG source code
• Batch update DAGs
• Reparse DAG files

DAG Runs

• List, create, view, update, and delete DAG runs
• Clear DAG runs
• Set DAG run notes
• Access upstream dataset events

Tasks

• List DAG tasks
• View task details
• Manage task instances
• Clear task instances
• Set task instance states

Variables, Connections, and Pools

• Create, read, update, and delete operations for Airflow variables
• Manage connections with testing capability
• Configure and manage worker pools

Additional Features

• XCom management
• Dataset operations
• Health monitoring
• DAG statistics
• Configuration access
• Plugin and provider information
• Event logs and system information

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "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"}}'

See the official Claude Code MCP documentation for more details.

For 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 > Tools & Integrations and click "New MCP Server".

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

{
    "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"
            }
        }
    }
}

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 explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "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"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect