Airflow + NVIDIA Agent Intelligence Toolkit: Complete MCP Integration
Airflow is a MCP server that A MCP Server that connects to Apache Airflow using official python client..
When integrated with NVIDIA Agent Intelligence Toolkit, 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 NVIDIA Agent Intelligence Toolkit, 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 NVIDIA Agent Intelligence Toolkit
- 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
- NVIDIA Agent Intelligence Toolkit installed and configured
- Compatible operating system (Python Package (pip), Docker Container, Framework Integration)
Installation
Step 1: Install Airflow
Configuration
Step 2: Configure NVIDIA Agent Intelligence Toolkit
- Open NVIDIA Agent Intelligence Toolkit 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 NVIDIA Agent Intelligence Toolkit:
Pipeline Monitoring
undefined
Ask NVIDIA Agent Intelligence Toolkit: "Check status of all DAGs and recent failures"
Expected Result: undefined
Manual DAG Execution
undefined
Ask NVIDIA Agent Intelligence Toolkit: "Trigger monthly_report DAG with date parameter"
Expected Result: undefined
Troubleshooting Failed Tasks
undefined
Ask NVIDIA Agent Intelligence Toolkit: "Show failed tasks in data_pipeline and their error logs"
Expected Result: undefined
Testing Your Setup
- Launch NVIDIA Agent Intelligence Toolkit
- Verify Airflow is available in the tools list
- Test basic Airflow functionality
Troubleshooting
Common Issues
MCP Server Connection Failed
Symptoms: Connection refused errors, Timeout connecting to MCP server, URL not responding
Cause: MCP server not running or incorrect URL configuration
Solution:
- Verify MCP server is running and accessible
- Check URL in configuration matches server endpoint
- Ensure network/firewall allows connection to server port
- Test connection with curl or browser before agent integration
Tool Schema Validation Errors
Symptoms: Invalid input format errors, Schema mismatch warnings, Type validation failures
Cause: Input data does not match MCP tool schema
Solution:
- Use CLI to inspect tool schema: aiq info mcp --url <url> --tool <name>
- Validate input data matches expected types and required fields
- Check JSON schema definitions in MCP server documentation
- Convert inputs to proper format (dict, JSON string, or schema instance)
Framework Integration Issues
Symptoms: Import errors, Framework not found, Incompatible versions
Cause: Missing or incompatible framework dependencies
Solution:
- Ensure target framework (LangChain, LlamaIndex, etc.) is installed
- Check version compatibility between AIQ toolkit and framework
- Install framework-specific dependencies as needed
- Refer to documentation for framework-specific configuration
Performance Bottlenecks
Symptoms: Slow agent responses, High token usage, Workflow timeouts
Cause: Inefficient tool usage or workflow design
Solution:
- Enable observability to identify bottlenecks
- Use profiling features to analyze tool and agent performance
- Review token tracking metrics to optimize LLM calls
- Consider hyperparameter tuning for agent optimization
OpenTelemetry Integration Errors
Symptoms: Observability data not appearing, Telemetry export failures, Missing metrics
Cause: OpenTelemetry not properly configured
Solution:
- Verify OpenTelemetry collector is running
- Check observability configuration in AIQ settings
- Ensure proper instrumentation of agent workflows
- Review OpenTelemetry export settings and endpoints
Airflow not appearing in NVIDIA Agent Intelligence Toolkit
Symptoms: Server not listed, Tools not available
Cause: Configuration or installation issue
Solution:
- Verify configuration syntax
- Check Airflow installation
- Restart NVIDIA Agent Intelligence Toolkit
- Check logs for error messages
Next Steps
Now that Airflow is integrated with NVIDIA Agent Intelligence Toolkit:
- Explore all Airflow capabilities through NVIDIA Agent Intelligence Toolkit
- Check out other MCP servers that work with NVIDIA Agent Intelligence Toolkit
- Join the MCP community for tips and support
- Consider contributing to Airflow development
Need Help?
- Search for Airflow documentation
- Check the NVIDIA Agent Intelligence Toolkit MCP guide
- Join the MCP community discussions