Airflow Mcp Server
Let your agent inspect and manage Apache Airflow DAGs and metadata via MCP with optional read-only --safe mode.
Overview
Airflow MCP Server is an Operate-phase MCP server that exposes Apache Airflow API operations to agents with optional read-only --safe tooling.
What is this MCP server?
- MCP bridge to Apache Airflow API (PyPI airflow-mcp-server 0.9.0)
- --safe flag limits tools to read-only operations
- --static-tools option versus hierarchical discovery
- stdio PyPI package plus streamable-http on localhost:3000
- Requires AIRFLOW_BASE_URL and AUTH_TOKEN (JWT)
- PyPI package version 0.9.0 (HTTP variant notes 0.8.2)
- Two CLI flags documented: --safe and --static-tools
- Two required env vars: AIRFLOW_BASE_URL and AUTH_TOKEN
Community signal: 33 GitHub stars.
What problem does it solve?
Debugging Airflow DAGs from the UI is slow, and agents cannot help without authenticated API access wrapped as tools.
Who is it for?
Solo builders or tiny teams already running Airflow who want agent-assisted ops and investigation from the IDE.
Skip if: Projects with no Airflow deployment or beginners who do not want to manage JWT tokens and API URLs.
What do I get? / Deliverables
After setting base URL and JWT token, your agent can query—and optionally control—Airflow through MCP with a read-only safe mode when you need it.
- Agent-callable Airflow API tools via MCP
- Optional read-only tool surface with --safe
- stdio or local streamable-http transport choice
Recommended MCP Servers
Journey fit
How it compares
Airflow orchestration MCP, not a general cloud control plane or codebase RAG server.
Common Questions / FAQ
Who is Airflow MCP Server for?
Developers operating Apache Airflow pipelines who use MCP agents and want API-backed DAG and run visibility from their editor.
When should I use Airflow MCP Server?
Use it in Operate when debugging failed runs, auditing DAG state, or safely exploring metadata with --safe read-only tools.
How do I add Airflow MCP Server to my agent?
Install airflow-mcp-server from PyPI with stdio transport or run the HTTP variant, set AIRFLOW_BASE_URL and AUTH_TOKEN, and register the server in MCP settings.