Airflow + BoltAI: Complete MCP Integration
Airflow is a MCP server that A MCP Server that connects to Apache Airflow using official python client..
When integrated with BoltAI, 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 BoltAI, 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 BoltAI
- 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
- BoltAI installed and configured
- Compatible operating system (macOS)
Installation
Step 1: Install Airflow
Configuration
Step 2: Configure BoltAI
- Open BoltAI 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 BoltAI:
Pipeline Monitoring
undefined
Ask BoltAI: "Check status of all DAGs and recent failures"
Expected Result: undefined
Manual DAG Execution
undefined
Ask BoltAI: "Trigger monthly_report DAG with date parameter"
Expected Result: undefined
Troubleshooting Failed Tasks
undefined
Ask BoltAI: "Show failed tasks in data_pipeline and their error logs"
Expected Result: undefined
Testing Your Setup
- Launch BoltAI
- Verify Airflow is available in the tools list
- Test basic Airflow functionality
Troubleshooting
Common Issues
Installation Failed
Symptoms: Download errors, Installation not completing
Cause: macOS security settings or corrupted download
Solution:
- Check macOS security preferences allow app installation
- Re-download installer from official website
- Try installing via Homebrew as alternative
- Ensure sufficient disk space and admin permissions
MCP Server Not Found
Symptoms: Server command not found, Path errors
Cause: Server not installed or not in PATH
Solution:
- Verify MCP server installation using Terminal
- Use absolute path to server executable
- Check server executable permissions (chmod +x)
- Test server command from Terminal first
Connection Fails
Symptoms: Server status shows disconnected, Connection timeout
Cause: Server configuration or environment issues
Solution:
- Check server configuration parameters
- Verify environment variables are set correctly
- Restart BoltAI after configuration changes
- Check macOS firewall and security settings
Tools Not Available in Conversation
Symptoms: Server connected but tools not accessible, Limited functionality
Cause: Tool registration or permission issues
Solution:
- Verify server implements MCP protocol correctly
- Check BoltAI permissions for tool access
- Restart conversation or create new chat session
- Review server logs for tool registration errors
Airflow not appearing in BoltAI
Symptoms: Server not listed, Tools not available
Cause: Configuration or installation issue
Solution:
- Verify configuration syntax
- Check Airflow installation
- Restart BoltAI
- Check logs for error messages
Next Steps
Now that Airflow is integrated with BoltAI:
- Explore all Airflow capabilities through BoltAI
- Check out other MCP servers that work with BoltAI
- Join the MCP community for tips and support
- Consider contributing to Airflow development
Need Help?
- Search for Airflow documentation
- Check the BoltAI MCP guide
- Join the MCP community discussions