Airflow + MCP Inspector: Complete MCP Integration

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

When integrated with MCP Inspector, 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 MCP Inspector, 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 MCP Inspector
• 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
• MCP Inspector installed and configured
• Compatible operating system (CLI Tool)

Installation

Step 1: Install Airflow

Configuration

Step 2: Configure MCP Inspector

1. Open MCP Inspector 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 MCP Inspector:

Pipeline Monitoring

undefined

Ask MCP Inspector: "Check status of all DAGs and recent failures"

Expected Result: undefined

Manual DAG Execution

undefined

Ask MCP Inspector: "Trigger monthly_report DAG with date parameter"

Expected Result: undefined

Troubleshooting Failed Tasks

undefined

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

Expected Result: undefined

Testing Your Setup

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

Troubleshooting

Common Issues

Connection Failed

Symptoms: Inspector UI shows "Disconnected"

Cause: Server process exited or failed to start.

Solution:

• Check the terminal where you ran npx ... for error output from your server.
• Ensure your server prints JSON-RPC messages to stdout.

Tools Not Showing

Symptoms: Tool list is empty

Cause: Server did not send tools/list response or capabilities negotiation failed.

Solution:

• Check the "Console" or "Logs" tab in the Inspector to see the raw communication.
• Verify your server code correctly implements the ListToolsRequest handler.

Airflow not appearing in MCP Inspector

Symptoms: Server not listed, Tools not available

Cause: Configuration or installation issue

Solution:

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

Next Steps

Now that Airflow is integrated with MCP Inspector:

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

Need Help?

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