Airflow MCP

🚀 Airflow MCP Server

This project is an MCP (Model Context Protocol) server integrated with Apache Airflow, offering various tools to manage and monitor Airflow DAG runs. It supports operations such as triggering DAGs, getting DAG statuses, backfilling data, and retrieving logs.

✨ Features

• Trigger DAG (trigger-dag): Trigger the execution of a specified DAG.
• Enable DAG (enable-dag): Enable a specified DAG.
• Get Daily Report (get-daily-report): Obtain a summary report of all DAG runs within a specified time range.
• List All DAGs (list-dags): List all available DAGs.
• Batch Retrieve DAG Run Records (list-dag-runs): Retrieve DAG run records in batches.
• Get DAG Run Status (get-dag-status): Get the run status of a specific DAG.
• Get DAG Logs (get-dag-logs): Retrieve the logs of a DAG run.
• Backfill DAG (backfill-dag): Backfill DAG data within a specified date range.

💻 Usage Examples

Basic Usage

{
  "mcpServers": {
    "airflow": {
      "command": "uvx",
      "args": [
        "airflow-mcp"
      ],
      "env": {
        "AIRFLOW_API_BASE": "http://localhost:8000/api/v1",
        "AIRFLOW_USERNAME": "admin",
        "AIRFLOW_PASSWORD": "admin"
      }
    }
  }
}

📦 Installation

Development Setup

1. Synchronize the code.
2. Modify mcp_config.json and add Airflow configuration.

{
  "mcpServers": {
    "airflow": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/airflow-mcp",
        "run",
        "airflow_mcp.py"
      ],
      "env": {
        "AIRFLOW_API_BASE": "http://localhost:8000/api/v1",
        "AIRFLOW_USERNAME": "admin",
        "AIRFLOW_PASSWORD": "admin"
      }
    }
  }
}

3. Start an Airflow instance.

mkdir ~/airflow-docker
cd ~/airflow-docker
curl -LfO 'https://airflow.apache.org/docs/apache-airflow/2.8.3/docker-compose.yaml'
cat << EOF > .env
AIRFLOW_UID=$(id -u)
AIRFLOW__CORE__LOAD_EXAMPLES=false
AIRFLOW__CORE__EXECUTOR=SequentialExecutor
EOF
docker compose up -d

🤝 Contribution

Contributions are welcome! Please submit a Pull Request and ensure that you follow the project's coding standards.

📄 License

This project is licensed under the MIT License.