Apache Airflow MCP server for AI agents

The Apache Airflow MCP Server is a standardized implementation that wraps Apache Airflow's REST API using the Model Context Protocol (MCP), allowing MCP clients to interact with Airflow through a consistent interface. It supports comprehensive Airflow functionality including DAG management, task execution, variables, connections, and more.

Installation

Setting Up the Environment

Before using the MCP server, you need to configure the following environment variables:

AIRFLOW_HOST=<your-airflow-host>        # Optional, defaults to http://localhost:8080
AIRFLOW_USERNAME=<your-airflow-username>
AIRFLOW_PASSWORD=<your-airflow-password>
AIRFLOW_API_VERSION=v1                  # Optional, defaults to v1

Installation Options

You can install the Apache Airflow MCP Server via Smithery:

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

Usage

Configuration with Claude Desktop

Add the MCP server 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"
      }
    }
  }
}

Using Read-Only Mode

For increased safety, you can run the server in read-only mode:

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

In read-only mode, the server only exposes tools that perform read operations and excludes operations that create, update, or delete resources.

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"
      }
    }
  }
}

Selecting Specific API Groups

You can select specific API groups to use:

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

Available API groups:

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

Manual Execution

Run the server manually:

make run

Options:

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

Or run the SSE server directly:

make run-sse

You can also start the service directly using uv:

uv run src --transport http --port 8080

Supported Features

The MCP server supports a wide range of Apache Airflow features, including:

DAG Management

List, get details, pause/unpause, update, and delete DAGs
Access DAG source code
Patch multiple DAGs
Reparse DAG files

DAG Runs

List, create, get details, update, and delete DAG runs
Clear DAG runs and set notes
Get upstream dataset events

Tasks

List DAG tasks and get task details
Manage task instances
Clear task instances and set their state
List task instance tries

Variables, Connections, and Pools

Full CRUD operations for Variables
Full CRUD operations for Connections
Full CRUD operations for Pools

Additional Features

XComs management
Datasets operations
System monitoring and health checks
Configuration access
Plugins and providers management
Event logs access

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "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"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "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"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "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"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect

Apache Airflow MCP server