This MCP server allows control of Airflow via its APIs, supporting both standard input/output and HTTP transport protocols.
From the registry: An MCP server for Apache Airflow
Please install the `airflow-mcp-server` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Airflow 3.0 instance** — A reachable Airflow 3 API with JWT auth. (https://airflow.apache.org)
- **Airflow JWT token** — JWT token for authenticating against the Airflow API (only auth method supported in Airflow 3.0).
Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["airflow-mcp-server","--base-url","http://localhost:8080","--auth-token","<jwt_token>"]
Note: Supports --safe (read-only) mode. Also supports HTTP transport via --http --port 3000. Do not include /api/v2 in base URL.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.AUTH_TOKENrequiredJWT token required for authentication.Real-time Kubernetes network traffic visibility and API analysis for HTTP, gRPC, Redis, Kafka, DNS.