MCP Airflow Simple MCP Server

A **Model Context Protocol (MCP) server** for Apache Airflow 3 that provides essential tools for DAG management, monitoring, debugging, and

Local serverstdioPython

What is the MCP Airflow Simple MCP server?

MCP Airflow Simple MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. A Model Context Protocol (MCP) server for Apache Airflow 3 that provides essential tools for DAG management, monitoring, debugging, and connection testing through the Airflow REST API v2.

Setting it up

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

What the assistant can call

Once MCP Airflow Simple is connected, these are the calls the assistant has available:

  • get_dags — List all DAGs in Airflow. json { "only_active": false, "limit": 100 }
  • get_dag_tasks — Get all tasks in a specific DAG. json { "dag_id": "example_dag" }
  • trigger_dag_run — Trigger a new DAG run. json { "dag_id": "example_dag", "conf": {"key": "value"}, "logical_date": "2026-01-05T00:00:00Z" }
  • clear_dag_run — Clear/retry a DAG run (resets failed tasks). json { "dag_id": "example_dag", "dag_run_id": "manual__2026-01-05T00:00:00+00:00", "dry_run": false }
  • set_dag_state — The set_dag_state tool exposed by this server
  • get_dag_runs — Get DAG run history with optional state filtering. json { "dag_id": "example_dag", "state": "failed", "limit": 25 }
  • get_task_instances — Get task instances for a specific DAG run. json { "dag_id": "example_dag", "dag_run_id": "manual__2026-01-05T00:00:00+00:00" }
  • get_dag_stats — The get_dag_stats tool exposed by this server
  • get_task_logs — Get execution logs for a specific task instance. json { "dag_id": "example_dag", "dag_run_id": "manual__2026-01-05T00:00:00+00:00", "task_id"
  • get_import_errors — The get_import_errors tool exposed by this server
  • get_connections — List all Airflow connections. json { "limit": 100 }
  • get_connection — Get details of a specific connection. json { "connection_id": "postgres_default" }

Configuration and credentials

You will need one environment variable: GIT_AUTO_UPDATE. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

  • Python 3.8+ - Apache Airflow 3.x with REST API enabled - Network access to Airflow instance

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch MCP Airflow Simple.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the mcp airflow simple mcp server does with a few real requests.

Choosing this one

Among the monitoring and observability options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. MCP Airflow Simple's toolset — get_dags, get_dag_tasks, trigger_dag_run and 11 more — is a fair guide to whether it matches your workflow. It is maintained by chayasin; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Available tools

ToolWhat it does
get_dagsList all DAGs in Airflow. json { "only_active": false, "limit": 100 }
get_dag_tasksGet all tasks in a specific DAG. json { "dag_id": "example_dag" }
trigger_dag_runTrigger a new DAG run. json { "dag_id": "example_dag", "conf": {"key": "value"}, "logical_date": "2026-01-05T00:00:00Z" }
clear_dag_runClear/retry a DAG run (resets failed tasks). json { "dag_id": "example_dag", "dag_run_id": "manual__2026-01-05T00:00:00+00:00", "dry_run": false }
set_dag_stateThe set_dag_state tool exposed by this server.
get_dag_runsGet DAG run history with optional state filtering. json { "dag_id": "example_dag", "state": "failed", "limit": 25 }
get_task_instancesGet task instances for a specific DAG run. json { "dag_id": "example_dag", "dag_run_id": "manual__2026-01-05T00:00:00+00:00" }
get_dag_statsThe get_dag_stats tool exposed by this server.
get_task_logsGet execution logs for a specific task instance. json { "dag_id": "example_dag", "dag_run_id": "manual__2026-01-05T00:00:00+00:00", "task_id": "example_task", "try_number": 1 }
get_import_errorsThe get_import_errors tool exposed by this server.
get_connectionsList all Airflow connections. json { "limit": 100 }
get_connectionGet details of a specific connection. json { "connection_id": "postgres_default" }
test_connectionTest connection accessibility. json { "connection_id": "postgres_default" }
check_healthCheck Airflow system health (includes Metadatabase, Scheduler, Triggerer, and DagProcessor). json {}

How to install the MCP Airflow Simple MCP server

{
  "mcpServers": {
    "airflow": {
      "command": "python",
      "args": ["c:\\{path_to_your_folder}\\mcp-airflow-simple\\server.py"],
      "env": {
        "GIT_AUTO_UPDATE": "true"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

  • Python 3.8+ - Apache Airflow 3.x with REST API enabled - Network access to Airflow instance
VariableDescriptionRequired
GIT_AUTO_UPDATEConfiguration value read at startup.Optional

Example prompts to try

  • Use MCP Airflow Simple to get dags.
  • Use MCP Airflow Simple to get dag tasks.
  • Use MCP Airflow Simple to trigger dag run.

Frequently asked questions

It connects MCP Airflow Simple to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (get_dags, get_dag_tasks, trigger_dag_run, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with MCP Airflow Simple directly.