Airflow + Claude Code: Complete MCP Integration

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

When integrated with Claude Code, 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 Claude Code, 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 Claude Code
• 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
• Claude Code installed and configured
• Compatible operating system (Windows, macOS, Linux)

Installation

Step 1: Install Airflow

Configuration

Step 2: Configure Claude Code

1. Install Claude Code

Download and install Claude Code from the official website

Visit: https://claude.ai/code

Note: Claude Code is available as a native application, not via npm

2. Navigate to Project

Open terminal in your project directory where you want to use the MCP server

3. Install MCP Server

Install the MCP server you want to use (e.g., via npm, pip, or other package manager)

4. Configure MCP Server

Add MCP server configuration to project CLAUDE.md file or use --mcp-config flag

Note: CLAUDE.md is preferred for project-specific configuration

5. Test Integration

Start Claude Code and verify MCP server is working

claude

Note: Use interactive mode to test MCP server functionality

Configuration Details

Add to your project's CLAUDE.md file:

## MCP Servers

### Airflow
- **Installation**: airflow
- **Configuration**: "AIRFLOW_HOST": "http://localhost:8080",
        "AIRFLOW_USERNAME": "admin",
        "AIRFLOW_PASSWORD": "admin_password",
        "AIRFLOW_READ_ONLY": "true"
- **Description**: A MCP Server that connects to Apache Airflow using official python client.

Claude Code will automatically detect and load MCP servers from your project context.

Examples

Once configured, you can use Airflow in Claude Code:

Pipeline Monitoring

undefined

Ask Claude Code: "Check status of all DAGs and recent failures"

Expected Result: undefined

Manual DAG Execution

undefined

Ask Claude Code: "Trigger monthly_report DAG with date parameter"

Expected Result: undefined

Troubleshooting Failed Tasks

undefined

Ask Claude Code: "Show failed tasks in data_pipeline and their error logs"

Expected Result: undefined

Testing Your Setup

1. Run claude in your project directory
2. Ask Claude to list available tools and verify Airflow tools are present
3. Test Airflow functionality by asking Claude to use specific tools

Test commands:

claude

claude --debug

Troubleshooting

Common Issues

Server Not Found

Symptoms: Command not found errors, Server tools unavailable

Cause: Server not installed or not in PATH

Solution:

• Verify server installation
• Check PATH environment variable
• Install server globally or in project

Configuration Not Loaded

Symptoms: CLAUDE.md changes not recognized, Old server config used

Cause: CLAUDE.md file not in correct location or format

Solution:

• Ensure CLAUDE.md is in project root
• Verify markdown syntax is correct
• Restart Claude Code session

Airflow not appearing in Claude Code

Symptoms: Server not listed, Tools not available

Cause: Configuration or installation issue

Solution:

• Verify configuration syntax
• Check Airflow installation
• Restart Claude Code
• Check logs for error messages

Next Steps

Now that Airflow is integrated with Claude Code:

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

Need Help?

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