Apache Airflow MCP server for AI agents

This MCP server implementation for Apache Airflow provides a standardized way to interact with Airflow through the Model Context Protocol. It wraps Airflow's REST API, making it accessible to MCP clients and providing comprehensive access to Airflow's functionality.

Installation

Prerequisites

This package requires the Apache Airflow client library, which will be automatically installed as a dependency.

Installing the Package

You can install the package using pip:

pip install mcp-server-apache-airflow

Configuration

The server requires configuration through environment variables:

AIRFLOW_HOST=<your-airflow-host>        # Optional, defaults to http://localhost:8080
AIRFLOW_API_VERSION=v1                  # Optional, defaults to v1
READ_ONLY=true                          # Optional, enables read-only mode (defaults to false)

Authentication Options

You need to provide authentication credentials using one of these methods:

Basic Authentication (username/password):

AIRFLOW_USERNAME=<your-airflow-username>
AIRFLOW_PASSWORD=<your-airflow-password>

JWT Token Authentication:

AIRFLOW_JWT_TOKEN=<your-jwt-token>

To obtain a JWT token from Airflow:

curl -X 'POST' \
  "http://localhost:8080/auth/token" \
  -H 'Content-Type: application/json' \
  -d '{ "username": "<your-username>", "password": "<your-password>" }'

Usage

Running the Server

You can run the server using uv or uvx:

# Basic usage
uvx mcp-server-apache-airflow

# With read-only mode
uvx mcp-server-apache-airflow --read-only

# Selecting specific API groups
uvx mcp-server-apache-airflow --apis dag --apis dagrun

Available API groups:

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

Claude Desktop Integration

Add the server 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"
      }
    }
  }
}

For read-only mode (recommended for safety):

{
  "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",
        "READ_ONLY": "true"
      }
    }
  }
}

Alternative Installation with Smithery

You can also install the server for Claude Desktop using Smithery:

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

Manual Execution Options

You can run the server manually with different transport options:

# Run with default settings
make run

# Run with specific transport and port
uvx mcp-server-apache-airflow --transport http --port 8080

Transport options:

stdio (default)
sse
http

Supported Features

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

DAG Management

List, get details, pause/unpause, update, and delete DAGs
Access DAG source code
Reparse DAG files

DAG Runs

List, create, update, and delete DAG runs
Clear DAG runs
Manage dataset events

Task Management

List DAG tasks and task instances
Update task instances
Access task logs
Set task instance state

Resource Management

Variables: Create, list, update, delete
Connections: Create, list, update, delete, test
Pools: Create, list, update, delete
XComs: List and retrieve

Monitoring and System

Health status
Configuration
Plugins and providers
Event logs
Import errors
Version 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