beginner⏱️ 18-28 minutes📅 Updated June 2026

Step-by-step guide to integrate Airflow MCP server with mcphub.nvim. Includes list_dags and trigger_dag.

Airflow + mcphub.nvim: Complete MCP Integration

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

When integrated with mcphub.nvim, 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 mcphub.nvim, 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 mcphub.nvim
  • 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
  • mcphub.nvim installed and configured
  • Compatible operating system (Neovim)

Installation

Step 1: Install Airflow

Configuration

Step 2: Configure mcphub.nvim

  1. Locate your configuration file:

    • Windows: %LOCALAPPDATA%\mcphub\servers.json
    • macOS: ~/.config/mcphub/servers.json
    • Linux: ~/.config/mcphub/servers.json
  2. Add server configuration:

{
  "mcpServers": {
    "airflow": {
      "command": "airflow",
      "args": [],
      "env": {
        "AIRFLOW_HOST": "http://localhost:8080",
        "AIRFLOW_USERNAME": "admin",
        "AIRFLOW_PASSWORD": "admin_password",
        "AIRFLOW_READ_ONLY": "true"
      }
    }
  }
}

  1. Restart mcphub.nvim

Completely quit and restart mcphub.nvim to load the new configuration.

Examples

Once configured, you can use Airflow in mcphub.nvim:

Pipeline Monitoring

undefined

Ask mcphub.nvim: "Check status of all DAGs and recent failures"

Expected Result: undefined

Manual DAG Execution

undefined

Ask mcphub.nvim: "Trigger monthly_report DAG with date parameter"

Expected Result: undefined

Troubleshooting Failed Tasks

undefined

Ask mcphub.nvim: "Show failed tasks in data_pipeline and their error logs"

Expected Result: undefined

Testing Your Setup

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

Troubleshooting

Common Issues

Servers not showing in :McpHub

Symptoms: Empty server list, Configuration not loaded

Cause: Incorrect configuration file path or JSON syntax error

Solution:

  • Verify servers.json exists in ~/.config/mcphub/ or .vscode/mcp.json in project root
  • Check JSON syntax for errors (trailing commas, missing quotes)
  • Run :checkhealth mcphub to diagnose issues

Tool execution fails

Symptoms: Error message when AI tries to use tool, No response

Cause: Server command failed or environment variables missing

Solution:

  • Check server logs in :McpHub
  • Verify "command" path is correct and executable
  • Ensure required environment variables are set in the config

Chat plugin not recognizing tools

Symptoms: AI says it cannot perform the action, Tools not listed in chat

Cause: Integration issue with the specific chat plugin

Solution:

  • Ensure you are using a supported version of the chat plugin
  • Check mcphub.nvim documentation for plugin-specific setup instructions
  • Restart Neovim to reload the integration

Airflow not appearing in mcphub.nvim

Symptoms: Server not listed, Tools not available

Cause: Configuration or installation issue

Solution:

  • Verify configuration syntax
  • Check Airflow installation
  • Restart mcphub.nvim
  • Check logs for error messages

Next Steps

Now that Airflow is integrated with mcphub.nvim:

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

Need Help?

Related Resources

More Integrations

Explore other MCP servers that work with mcphub.nvim

Need Help?

Join the MCP community for support and discussions

Airflow + mcphub.nvim: MCP Setup Guide (2026)