Airflow + Genkit: Complete MCP Integration
Airflow is a MCP server that A MCP Server that connects to Apache Airflow using official python client..
When integrated with Genkit, 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 Genkit, 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 Genkit
- 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
- Genkit installed and configured
- Compatible operating system (Node.js, Cross-platform, Google Cloud)
Installation
Step 1: Install Airflow
Configuration
Step 2: Configure Genkit
- Open Genkit settings
- Navigate to MCP server configuration
- Add Airflow server with appropriate settings
- Save and restart if needed
Examples
Once configured, you can use Airflow in Genkit:
Pipeline Monitoring
undefined
Ask Genkit: "Check status of all DAGs and recent failures"
Expected Result: undefined
Manual DAG Execution
undefined
Ask Genkit: "Trigger monthly_report DAG with date parameter"
Expected Result: undefined
Troubleshooting Failed Tasks
undefined
Ask Genkit: "Show failed tasks in data_pipeline and their error logs"
Expected Result: undefined
Testing Your Setup
- Launch Genkit
- Verify Airflow is available in the tools list
- Test basic Airflow functionality
Troubleshooting
Common Issues
Genkit Installation Failed
Symptoms: npm install errors, CLI not found
Cause: Node.js version or npm configuration issues
Solution:
- Verify Node.js 18+ is installed
- Clear npm cache and try again
- Check npm registry configuration
- Try using yarn instead of npm
MCP Plugin Not Loading
Symptoms: Plugin errors, MCP tools unavailable
Cause: Plugin installation or configuration issues
Solution:
- Verify @genkit-ai/mcp package is installed
- Check plugin configuration syntax
- Ensure plugin is properly imported
- Review Genkit logs for plugin errors
Server Connection Failed
Symptoms: MCP server not responding, Tool execution errors
Cause: Server installation or configuration problems
Solution:
- Verify MCP server installation
- Test server independently before Genkit integration
- Check server executable permissions
- Review server logs for connection issues
Flow Execution Errors
Symptoms: Flow fails, Runtime errors
Cause: Flow configuration or MCP integration issues
Solution:
- Check flow definition syntax
- Verify input/output schemas match usage
- Test flows incrementally with simpler operations
- Review Genkit execution logs for detailed errors
Airflow not appearing in Genkit
Symptoms: Server not listed, Tools not available
Cause: Configuration or installation issue
Solution:
- Verify configuration syntax
- Check Airflow installation
- Restart Genkit
- Check logs for error messages
Next Steps
Now that Airflow is integrated with Genkit:
- Explore all Airflow capabilities through Genkit
- Check out other MCP servers that work with Genkit
- Join the MCP community for tips and support
- Consider contributing to Airflow development
Need Help?
- Search for Airflow documentation
- Check the Genkit MCP guide
- Join the MCP community discussions