MCP-Airflow-API

Overview

MCP-Airflow-API is a comprehensive MCP server that transforms Apache Airflow REST API operations into natural language tools, allowing users to manage their Airflow clusters through intuitive commands rather than complex API calls. The project supports both Airflow 2.x (43 tools) and 3.0+ (45+ tools) with dynamic version selection via environment variables, making it adaptable to different Airflow deployments without code changes.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

• list_dags

  Retrieve a list of all DAGs in Airflow

  Try:Show me all DAGsTry:List all available DAGsTry:What DAGs do I have?
• get_dag_details

  Get detailed information about a specific DAG

  Try:Show me details for the ETL DAGTry:What's the configuration of my daily pipeline?
• trigger_dag

  Trigger a DAG run for a specific DAG

  Try:Run the data processing DAG nowTry:Trigger my ETL pipeline
• pause_dag

  Pause a DAG to prevent it from running

  Try:Pause the maintenance DAGTry:Stop the nightly reporting from running
• resume_dag

  Resume a paused DAG

  Try:Unpause the backup DAGTry:Enable the nightly reporting again
• get_dag_runs

  Get all runs for a specific DAG

  Try:Show me recent runs of the analytics DAGTry:When did the ETL pipeline last run?
• get_task_instances

  Get task instances for a specific DAG run

  Try:Show me the tasks from yesterday's runTry:What tasks were in the latest pipeline execution?
• get_task_log

  Get the log output for a specific task instance

  Try:Show me the log for the data quality check taskTry:What went wrong with the extraction task?
• get_variables

  Retrieve variables stored in Airflow

  Try:Show me all variablesTry:What's the value of the database URL variable?
• set_variable

  Create or update a variable in Airflow

  Try:Set the timeout variable to 3600Try:Create a new API key variable
• get_connections

  Get all connections configured in Airflow

  Try:Show me all database connectionsTry:What connections are configured?
• add_connection

  Add a new connection to Airflow

  Try:Add a new PostgreSQL connectionTry:Create a connection to the warehouse database

Comparable tools

Installation

uvx --python 3.12 mcp-airflow-api

{
  "mcpServers": {
    "mcp-airflow-api": {
      "command": "uvx",
      "args": ["--python", "3.12", "mcp-airflow-api"],
      "env": {
        "AIRFLOW_API_VERSION": "v2",
        "AIRFLOW_API_BASE_URL": "http://localhost:8080/api",
        "AIRFLOW_API_USERNAME": "airflow",
        "AIRFLOW_API_PASSWORD": "airflow"
      }
    }
  }
}

git clone https://github.com/call518/MCP-Airflow-API.git
cd MCP-Airflow-API
cp .env.example .env
# Edit .env with your Airflow API settings
docker-compose up -d

FAQ

Which Airflow versions are supported?

MCP-Airflow-API supports Airflow 2.x (API v1) with 43 tools and Airflow 3.0+ (API v2) with 45+ tools. The version is selected via the AIRFLOW_API_VERSION environment variable.

How does it handle authentication?

It supports both basic authentication (username/password) and bearer token authentication for streamable-http mode. Configuration is done through environment variables.

On Hacker News

Recent discussion from the developer community.

• Show HN: MCP-Server for Control Airflow Cluster▲ 2
  Story by call518 · 2025-08-17

Compare MCP-Airflow-API with