Airflow + SpinAI: Complete MCP Integration

Airflow is a MCP server that A MCP Server that connects to Apache Airflow using official python client..

When integrated with SpinAI, you can:

• List all available DAGs in Airflow
• Manually trigger a DAG run
• Get DAG run history and status

This guide provides step-by-step instructions to set up Airflow in SpinAI, including configuration, examples, and troubleshooting.

What You'll Achieve

After completing this setup:

• Airflow will be fully integrated and operational
• You can use Airflow tools directly in SpinAI
• All Airflow capabilities will be available for your workflows
• Access to 5 different tools

Prerequisites

Before starting, ensure you have:

• Airflow webserver host URL
• Airflow authentication username
• Airflow authentication password
• SpinAI installed and configured
• Compatible operating system (Node.js)

Installation

Step 1: Install Airflow

Configuration

Step 2: Configure SpinAI

1. Open SpinAI settings
2. Navigate to MCP server configuration
3. Add Airflow server with appropriate settings
4. Save and restart if needed

Examples

Once configured, you can use Airflow in SpinAI:

Pipeline Monitoring

undefined

Ask SpinAI: "Check status of all DAGs and recent failures"

Expected Result: undefined

Manual DAG Execution

undefined

Ask SpinAI: "Trigger monthly_report DAG with date parameter"

Expected Result: undefined

Troubleshooting Failed Tasks

undefined

Ask SpinAI: "Show failed tasks in data_pipeline and their error logs"

Expected Result: undefined

Testing Your Setup

1. Launch SpinAI
2. Verify Airflow is available in the tools list
3. Test basic Airflow functionality

Troubleshooting

Common Issues

Tool Execution Error

Symptoms: Agent fails to retrieve data

Cause: MCP server process crashed or returned invalid JSON

Solution:

• Enable debug logging in SpinAI
• Check stderr of the MCP server process

Timeout

Symptoms: Agent hangs on tool call

Cause: MCP server is unresponsive

Solution:

• Configure timeouts in createMCPTool options

Airflow not appearing in SpinAI

Symptoms: Server not listed, Tools not available

Cause: Configuration or installation issue

Solution:

• Verify configuration syntax
• Check Airflow installation
• Restart SpinAI
• Check logs for error messages

Next Steps

Now that Airflow is integrated with SpinAI:

• Explore all Airflow capabilities through SpinAI
• Check out other MCP servers that work with SpinAI
• Join the MCP community for tips and support
• Consider contributing to Airflow development

Need Help?

• Search for Airflow documentation
• Check the SpinAI MCP guide
• Join the MCP community discussions