Back
Marketplace/Apache Airflow

TL;DR

Apache Airflow is a Data Engineering MCP server that lets Claude Code, Cursor, Windsurf and any MCP-compatible AI agent trigger DAGs, inspect task runs, and manage Airflow workflows from any MCP client. Install in 1 minute with mcpizy install airflow.

🌀

Apache Airflow

Data Engineering

Last updated June 1, 2026 · By MCPizy team

Trigger DAGs, inspect task runs, and manage Airflow workflows from any MCP client.

Install Apache Airflow

Via MCPizy CLI (recommended):
mcpizy install airflow
Or run directly:
pip install mcp-server-airflow
View on GitHub

Works with

Claude Code
Claude Desktop
Cursor
Windsurf
VS Code + Copilot
Any MCP Client

More Data Engineering MCPs

📐

Reexpress

Statistical verification for search and data science workflows.

🌊

Apache Kafka

Produce and consume Kafka messages, inspect topics and consumer groups from AI agents.

Alternatives to Apache Airflow

If Apache Airflow doesn't fit your stack, these Data Engineering MCP servers solve similar problems.

🔄

Keboola

Build data workflows, integrations, and analytics on a single platform. ETL and data orchestration.

⛏️

Powerdrill

Smart data analysis and visualization. Natural language queries over your datasets.

🗂️

Atlan

Metadata capabilities from Atlan for data governance and cataloging.

Key Takeaways

  • Apache Airflow exposes an MCP interface for data engineering workflows in Claude Code, Cursor and Windsurf.
  • No authentication required — works out of the box once installed.
  • Install in 1 command: mcpizy install airflow — config written to your client automatically.
  • Free and open source (GitHub source linked above) — verified compatible with every MCP client (Claude Code, Claude Desktop, Cursor, Windsurf, VS Code + Copilot).
  • Best use case: automate data engineering workflows from your AI agent without leaving the editor.

Frequently asked questions

What is the Apache Airflow MCP server?

The Apache Airflow MCP server is an Data Engineering Model Context Protocol server that lets Claude Code, Cursor, Windsurf, VS Code with Copilot, and other MCP-compatible AI agents trigger DAGs, inspect task runs, and manage Airflow workflows from any MCP client. It exposes Apache Airflow's capabilities as tools the AI can call directly from your editor or CLI.

How do I install Apache Airflow MCP with Claude Code?

The fastest way is the MCPizy CLI: run `mcpizy install airflow` and MCPizy will add the server to your `.claude.json` automatically. You can also install it manually by adding an entry under `mcpServers` in `.claude.json` with the command `pip install mcp-server-airflow` and restarting Claude Code.

Is Apache Airflow MCP free?

Yes. The Apache Airflow MCP server is free and open source (see the GitHub repository linked on this page). You may still need a Apache Airflow account or API key to connect the server to the underlying service, but the MCP layer itself has no MCPizy subscription cost.

Does Apache Airflow MCP work with Cursor and Windsurf?

Yes. Any MCP-compatible client works — including Claude Code, Claude Desktop, Cursor (via `.cursor/mcp.json`), Windsurf, VS Code with Copilot Chat, and custom agents built on the MCP SDK. The same install command targets all of them; only the config file path differs.

What can I do with Apache Airflow MCP?

Once installed, your AI agent can trigger DAGs, inspect task runs, and manage Airflow workflows from any MCP client directly inside your conversation. Typical use cases include asking Claude Code or Cursor to run Apache Airflow operations, inspect results, chain Apache Airflow with other MCP servers (see our Workflow Recipes), and automate repetitive data engineering tasks without leaving your editor.

Manage all your MCPs in one place

Monitor usage, track costs, and discover new MCPs.

Get Started Free