Airflow + gptme: Complete MCP Integration
Airflow is a MCP server that A MCP Server that connects to Apache Airflow using official python client..
When integrated with gptme, 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 gptme, 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 gptme
- 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
- gptme installed and configured
- Compatible operating system (Terminal, Python, Cross-platform)
Installation
Step 1: Install Airflow
Configuration
Step 2: Configure gptme
- Open gptme 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 gptme:
Pipeline Monitoring
undefined
Ask gptme: "Check status of all DAGs and recent failures"
Expected Result: undefined
Manual DAG Execution
undefined
Ask gptme: "Trigger monthly_report DAG with date parameter"
Expected Result: undefined
Troubleshooting Failed Tasks
undefined
Ask gptme: "Show failed tasks in data_pipeline and their error logs"
Expected Result: undefined
Testing Your Setup
- Launch gptme
- Verify Airflow is available in the tools list
- Test basic Airflow functionality
Troubleshooting
Common Issues
Installation Failed
Symptoms: pip install errors, Missing dependencies
Cause: Python environment or package conflicts
Solution:
- Use virtual environment for clean installation
- Update pip to latest version
- Install with pipx for isolation
- Check Python version compatibility
API Key Issues
Symptoms: Authentication errors, Model access denied
Cause: Missing or invalid API keys
Solution:
- Verify API keys are set correctly
- Check API key permissions and quotas
- Test API keys with curl or other tools
- Review model provider documentation
MCP Server Not Loading
Symptoms: Server load errors, Tools not available
Cause: Server configuration or installation issues
Solution:
- Verify server installation and PATH
- Check MCP server configuration syntax
- Test server independently before gptme integration
- Review gptme logs for connection errors
Terminal Display Issues
Symptoms: Formatting problems, Character encoding errors
Cause: Terminal compatibility or encoding issues
Solution:
- Ensure terminal supports UTF-8 encoding
- Try different terminal applications
- Check terminal color and formatting settings
- Update terminal application to latest version
Airflow not appearing in gptme
Symptoms: Server not listed, Tools not available
Cause: Configuration or installation issue
Solution:
- Verify configuration syntax
- Check Airflow installation
- Restart gptme
- Check logs for error messages
Next Steps
Now that Airflow is integrated with gptme:
- Explore all Airflow capabilities through gptme
- Check out other MCP servers that work with gptme
- Join the MCP community for tips and support
- Consider contributing to Airflow development
Need Help?
- Search for Airflow documentation
- Check the gptme MCP guide
- Join the MCP community discussions