Incident Response MCP for Apache Airflow for Gemini CLI
io.github.madamak/apache-airflow-mcp-server
Diagnose Airflow failures from UI links with bounded logs and optional recovery actions.
client:Gemini CLI
transport:stdio
runtime:pypi
Install Incident Response MCP for Apache Airflow in Gemini CLI
~/.gemini/settings.json · windows: %USERPROFILE%\.gemini\settings.json
{
"mcpServers": {
"apache-airflow-mcp-server": {
"command": "uvx",
"args": [
"apache-airflow-mcp-server"
],
"env": {
"AIRFLOW_MCP_HOST": "<AIRFLOW_MCP_HOST>",
"AIRFLOW_MCP_TOKEN": "<AIRFLOW_MCP_TOKEN>",
"AIRFLOW_MCP_USERNAME": "<AIRFLOW_MCP_USERNAME>",
"AIRFLOW_MCP_PASSWORD": "<AIRFLOW_MCP_PASSWORD>",
"AIRFLOW_MCP_API_VERSION": "<AIRFLOW_MCP_API_VERSION>",
"AIRFLOW_MCP_READ_ONLY": "<AIRFLOW_MCP_READ_ONLY>"
}
}
}
}
Gemini expands $VAR and ${VAR} inside env values, so a secret can live in your shell rather than this file. Gemini CLI docs