Airflow Mcp Server

io.github.abhishekbhakatPublished by GitHub account abhishekbhakatv0.9.0Updated Oct 27, 2026

An MCP server for Apache Airflow

VerifiedSTDIODesktop onlyCloud & InfrastructureDeveloper Tools

Overview

AI-generated overview

An MCP server that lets an assistant control an Apache Airflow 3 instance through its REST APIs, browsing DAGs, tasks and connections.

What you can do
  • Browse Airflow API operations by category (DAGs, tasks, connections and others) and pick the tool to run
  • Call Airflow REST endpoints against the configured instance, with read-only GET requests in safe mode
  • Expose all API operations as static tools at once instead of hierarchical discovery
  • Serve local Markdown guides as read-only resources for the assistant to reference
  • Run over stdio by default, or over Streamable HTTP for multiple clients
When to use it
Useful when you want an assistant to inspect or operate an Airflow 3 deployment — checking DAGs, tasks and connections, or triggering changes when unsafe mode is enabled — from a desktop MCP client.
Requirements
Runs locally as a Python package (for example via uvx). Needs the Airflow base URL without the /api/v2 suffix, and a valid JWT auth token supplied as AUTH_TOKEN or the --auth-token option. Network access to the Airflow instance is required; the server fetches the OpenAPI spec from the base URL.
Before you install
Unsafe mode is the default and allows modifying operations, not just reads; start with --safe if you only want read-only access. The JWT token grants Airflow API access, so keep it out of shared configs. The HTTP transport binds to localhost by default but can be exposed with --host.

Installation

In SourceWeft

  1. Open Airflow Mcp Server in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

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

[Image]

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)
json
{    "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
json
{    "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:

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

Uses Streamable HTTP for better scalability and web compatibility:

bash
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:

bash
airflow-mcp-server --safe

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

bash
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:

bash
airflow-mcp-server --static-tools

Command Line Options

bash
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:

bash
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

Source: README.md at commit e080477

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.9.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts