What is Apache Airflow

This project is a Model Context Protocol (MCP) server implementation for Apache Airflow that facilitates integration with MCP clients, enabling standardized interactions with Airflow’s REST API.

Use cases

This server can be used for managing Apache Airflow tasks, including creating and monitoring DAGs (Directed Acyclic Graphs), managing task instances and XComs, handling variables and connections, and performing health checks.

How to use

To use this MCP server, set required environment variables such as AIRFLOW_HOST, AIRFLOW_USERNAME, and AIRFLOW_PASSWORD. Then run the server using commands in a configuration setup for Claude Desktop or manually via the command line.

Key features

The server offers complete API coverage for DAG management, task management, variable and connection handling, as well as event logging and monitoring features. Each functionality is mapped to its respective API endpoint in Apache Airflow.

Where to use

This MCP server is suitable for environments utilizing Apache Airflow for workflow management, particularly when integration with various MCP clients is required, enhancing the flexibility and usability of Apache Airflow’s capabilities.

mcp-server-apache-airflow

A Model Context Protocol (MCP) server implementation for Apache Airflow, enabling seamless integration with MCP clients. This project provides a standardized way to interact with Apache Airflow through the Model Context Protocol.

About

This project implements a Model Context Protocol server that wraps Apache Airflow’s REST API, allowing MCP clients to interact with Airflow in a standardized way. It uses the official Apache Airflow client library to ensure compatibility and maintainability.

Feature Implementation Status

Setup

Dependencies

This project depends on the official Apache Airflow client library (apache-airflow-client). It will be automatically installed when you install this package.

Environment Variables

Set the following environment variables:

AIRFLOW_HOST=<your-airflow-host>
AIRFLOW_USERNAME=<your-airflow-username>
AIRFLOW_PASSWORD=<your-airflow-password>
AIRFLOW_API_VERSION=v1  # Optional, defaults to v1

Usage with Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "mcp-server-apache-airflow": {
      "command": "uvx",
      "args": [
        "mcp-server-apache-airflow"
      ],
      "env": {
        "AIRFLOW_HOST": "https://your-airflow-host",
        "AIRFLOW_USERNAME": "your-username",
        "AIRFLOW_PASSWORD": "your-password"
      }
    }
  }
}

Alternative configuration using uv:

{
  "mcpServers": {
    "mcp-server-apache-airflow": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/mcp-server-apache-airflow",
        "run",
        "mcp-server-apache-airflow"
      ],
      "env": {
        "AIRFLOW_HOST": "https://your-airflow-host",
        "AIRFLOW_USERNAME": "your-username",
        "AIRFLOW_PASSWORD": "your-password"
      }
    }
  }
}

Replace /path/to/mcp-server-apache-airflow with the actual path where you’ve cloned the repository.

Selecting the API groups

You can select the API groups you want to use by setting the --apis flag.

uv run mcp-server-apache-airflow --apis "dag,dagrun"

The default is to use all APIs.

Allowed values are:

• config
• connections
• dag
• dagrun
• dagstats
• dataset
• eventlog
• importerror
• monitoring
• plugin
• pool
• provider
• taskinstance
• variable
• xcom

Manual Execution

You can also run the server manually:

make run

make run accepts following options:

Options:

• --port: Port to listen on for SSE (default: 8000)
• --transport: Transport type (stdio/sse, default: stdio)

Or, you could run the sse server directly, which accepts same parameters:

make run-sse

Installing via Smithery

To install Apache Airflow MCP Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @yangkyeongmo/mcp-server-apache-airflow --client claude

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

The package is deployed automatically to PyPI when project.version is updated in pyproject.toml.
Follow semver for versioning.

Please include version update in the PR in order to apply the changes to core logic.

License

MIT License