Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
abhishekbhakat avatar

Airflow MCP

  • 33 repo stars
  • Updated October 14, 2025
  • abhishekbhakat/airflow-mcp-server

Airflow MCP Server is an MCP server that exposes Apache Airflow API operations to agents with optional read-only --safe tooling.

About

Airflow MCP Server connects coding agents to an existing Apache Airflow deployment through the Airflow REST API. Developers and small data teams running self-hosted or managed Airflow can expose DAG status, run history, and related operations as MCP tools so Claude Code or Cursor helps triage failures without living in the web UI. Configuration is explicit: set AIRFLOW_BASE_URL (for example http://localhost:8080) and a JWT AUTH_TOKEN; choose PyPI stdio install or a local streamable-http endpoint on port 3000. The --safe switch is important for operators who want the agent to diagnose but not trigger destructive changes. Use during Operate when pipelines are already in production; during Build only if Airflow is your core integration surface. Category aligns with data orchestration rather than generic cloud consoles.

  • 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)

Airflow MCP by the numbers

  • Data as of Aug 10, 2026 (Skillselion catalog sync)
terminal
claude mcp add --env AIRFLOW_BASE_URL=YOUR_AIRFLOW_BASE_URL --env AUTH_TOKEN=YOUR_AUTH_TOKEN airflow-mcp-server -- uvx airflow-mcp-server

Add your badge

Show developers this MCP server is listed on Skillselion. Paste this into your README.

Listed on Skillselion
repo stars33
Packageairflow-mcp-server
TransportSTDIO, HTTP
AuthRequired
Last updatedOctober 14, 2025
Repositoryabhishekbhakat/airflow-mcp-server

What it does

Let your agent inspect and manage Apache Airflow DAGs and metadata via MCP with optional read-only --safe mode.

Who is it for?

Best when you're already running Airflow and 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 you get

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

By the numbers

  • 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
README.md

airflow-mcp-server: An MCP Server for controlling Airflow 3

mcp-name: io.github.abhishekbhakat/airflow-mcp-server

MCPHub Certification

This MCP server is certified by MCPHub. This certification ensures that airflow-mcp-server follows best practices for Model Context Protocol implementation.

Find on Glama

Overview

A Model Context Protocol server for controlling Airflow via Airflow APIs.

Demo Video

https://github.com/user-attachments/assets/f3e60fff-8680-4dd9-b08e-fa7db655a705

Setup

Usage with Claude Desktop

Stdio Transport (Default)
{
    "mcpServers": {
        "airflow-mcp-server": {
            "command": "uvx",
            "args": [
                "airflow-mcp-server",
                "--base-url",
                "http://localhost:8080",
                "--auth-token",
                "<jwt_token>"
            ]
        }
    }
}

See CONFIG.md for IDE-specific configuration examples across popular MCP clients.

HTTP Transport
{
    "mcpServers": {
        "airflow-mcp-server-http": {
            "command": "uvx",
            "args": [
                "airflow-mcp-server",
                "--http",
                "--port",
                "3000",
                "--base-url",
                "http://localhost:8080",
                "--auth-token",
                "<jwt_token>"
            ]
        }
    }
}

Note:

  • Set base_url to the root Airflow URL (e.g., http://localhost:8080).
  • Do not include /api/v2 in the base URL. The server will automatically fetch the OpenAPI spec from ${base_url}/openapi.json.
  • Only JWT token is required for authentication. Cookie and basic auth are no longer supported in Airflow 3.0.

Transport Options

The server supports multiple transport protocols:

Stdio Transport (Default)

Standard input/output transport for direct process communication:

airflow-mcp-server --safe --base-url http://localhost:8080 --auth-token <jwt>
HTTP Transport

Uses Streamable HTTP for better scalability and web compatibility:

airflow-mcp-server --safe --http --port 3000 --base-url http://localhost:8080 --auth-token <jwt>

Note: SSE transport is deprecated. Use --http for new deployments as it provides better bidirectional communication and is the recommended approach by FastMCP.

Operation Modes

The server supports two operation modes:

  • Safe Mode (--safe): Only allows read-only operations (GET requests). This is useful when you want to prevent any modifications to your Airflow instance.
  • Unsafe Mode (--unsafe): Allows all operations including modifications. This is the default mode.

To start in safe mode:

airflow-mcp-server --safe

To explicitly start in unsafe mode (though this is default):

airflow-mcp-server --unsafe

Tool Discovery Modes

The server supports two tool discovery approaches:

  • Hierarchical Discovery (default): Tools are organized by categories (DAGs, Tasks, Connections, etc.). Browse categories first, then select specific tools. More manageable for large APIs.
  • Static Tools (--static-tools): All tools available immediately. Better for programmatic access but can be overwhelming.

To use static tools:

airflow-mcp-server --static-tools

Command Line Options

Usage: airflow-mcp-server [OPTIONS]

  MCP server for Airflow

Options:
  -v, --verbose      Increase verbosity
  -s, --safe         Use only read-only tools
  -u, --unsafe       Use all tools (default)
  --static-tools     Use static tools instead of hierarchical discovery
  --base-url TEXT    Airflow API base URL
  --auth-token TEXT  Authentication token (JWT)
  --http             Use HTTP (Streamable HTTP) transport instead of stdio
  --sse              Use Server-Sent Events transport (deprecated, use --http
                     instead)
  --port INTEGER     Port to run HTTP/SSE server on (default: 3000)
  --host TEXT        Host to bind HTTP/SSE server to (default: localhost)
  --help             Show this message and exit.

Using Resources

Point the server at a folder of Markdown guides whenever you want agents to reference local documentation:

airflow-mcp-server --base-url http://localhost:8080 --auth-token <jwt> --resources-dir ~/airflow-resources
  • Every top-level .md/.markdown file becomes a read-only resource (file:///<slug>) visible in your MCP client.
  • The first # Heading in each file (if present) is used as the resource title; otherwise the filename stem is used.
  • Set AIRFLOW_MCP_RESOURCES_DIR=/path/to/docs if you prefer environment-based configuration.
  • Update the files on disk and restart the server to refresh the resources list.

Considerations

Authentication

  • Only JWT authentication is supported in Airflow 3.0. You must provide a valid AUTH_TOKEN.

Page Limit

The default is 100 items, but you can change it using maximum_page_limit option in [api] section in the airflow.cfg file.

Transport Selection

  • Use stdio transport for direct process communication (default)
  • Use HTTP transport for web deployments, multiple clients, or when you need better scalability
  • Avoid SSE transport as it's deprecated in favor of HTTP transport

Recommended MCP Servers

How it compares

Airflow orchestration MCP, not a general cloud control plane or codebase RAG server.

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.

Data Analyticsinfradeploy

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.