Airflow Unfactor

airflow-unfactor

[](https://github.com/gabcoyne/airflow-unfactor/actions/workflows/test.yml) [](https://pypi.org/project/airflow-unfactor/) [](LICENSE)

An MCP server that converts Apache Airflow DAGs into Prefect flows. Point it at a DAG, and the LLM generates idiomatic Prefect code. Not a template with TODOs — working code. Built with FastMCP.

Install

[](https://cursor.com/install-mcp?name=airflow-unfactor&config=eyJjb21tYW5kIjoidXZ4IiwiYXJncyI6WyJhaXJmbG93LXVuZmFjdG9yIl19) [](https://insiders.vscode.dev/redirect/mcp/install?name=airflow-unfactor&config=%7B%22name%22%3A%22airflow-unfactor%22%2C%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22airflow-unfactor%22%5D%7D)

Claude Code — one line:

claude mcp add airflow-unfactor -- uvx airflow-unfactor

Claude Desktop and other clients — see [manual config](#manual-config) below.

Then ask your LLM: "Convert the DAG in dags/my_etl.py to a Prefect flow."

How It Works

The server exposes seven tools over MCP. The LLM reads raw DAG source code, looks up translation knowledge, and generates the Prefect flow.

| Tool | What It Does | |------|-------------| | read_dag | Returns raw DAG source code with metadata (path, size, line count) | | lookup_concept | Airflow→Prefect translation knowledge — operators, patterns, connections | | validate | Syntax-checks generated code and returns both sources for comparison | | search_prefect_docs | Searches live Prefect docs for anything not in the pre-compiled knowledge | | scaffold | Creates a Prefect project directory structure (not code) | | generate_deployment | Writes prefect.yaml deployment configuration from DAG metadata | | generate_migration_report | Writes MIGRATION.md with conversion decisions and a before-production checklist |

No AST parsing. No template engine. The LLM reads the code directly, just like a developer would.

Manual config

The buttons above and the claude mcp add command both register the server with uvx, which downloads it on first run — no separate pip install needed. To install the package directly anyway: pip install airflow-unfactor or uv pip install airflow-unfactor.

Claude Desktop — ~/Library/Application Support/Claude/claudedesktopconfig.json

{
  "mcpServers": {
    "airflow-unfactor": {
      "command": "uvx",
      "args": ["airflow-unfactor"]
    }
  }
}

Claude Code — .mcp.json in your project

{
  "mcpServers": {
    "airflow-unfactor": {
      "command": "uvx",
      "args": ["airflow-unfactor"]
    }
  }
}

Cursor — MCP settings

{
  "mcpServers": {
    "airflow-unfactor": {
      "command": "uvx",
      "args": ["airflow-unfactor"]
    }
  }
}

Example

Airflow DAG:

from airflow import DAG
from airflow.operators.python import PythonOperator

def extract():
    return {"users": [1, 2, 3]}

def transform(ti):
    data = ti.xcom_pull(task_ids="extract")
    return [u * 2 for u in data["users"]]

with DAG("my_etl", ...) as dag:
    t1 = PythonOperator(task_id="extract", python_callable=extract)
    t2 = PythonOperator(task_id="transform", python_callable=transform)
    t1 >> t2

Generated Prefect flow:

from prefect import flow, task

@task
def extract():
    return {"users": [1, 2, 3]}

@task
def transform(data):
    return [u * 2 for u in data["users"]]

@flow(name="my_etl")
def my_etl():
    data = extract()
    result = transform(data)
    return result

The >> dependency chain becomes explicit data passing through return values. XCom is gone. It's just Python.

Translation Knowledge

The server ships with 78 pre-compiled Airflow→Prefect translation entries covering operators, patterns, connections, and core concepts. These are compiled by Colin from live Airflow source and Prefect documentation.

When the pre-compiled knowledge doesn't cover something, search_prefect_docs queries the Prefect documentation MCP server at docs.prefect.io in real time.

Documentation

Full docs: gabcoyne.github.io/airflow-unfactor

Development

git clone https://github.com/gabcoyne/airflow-unfactor.git
cd airflow-unfactor
uv sync

# Run tests
uv run pytest

# Lint
uv run ruff check --fix

# Compile translation knowledge
cd colin && colin run

License

MIT — see [LICENSE](LICENSE).

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: gabcoyne
• Source: gabcoyne/airflow-unfactor
• License: MIT
• Homepage: https://gabcoyne.github.io/airflow-unfactor

Install and usage instructions live in the source repository linked above.