// SCAN REPORT

MCP Server for Apache Airflow

12 tools. 1 can modify or destroy data without limits.

1 write tool that can modify data. Rate limits recommended.

Last updated: 5 Jul 2026

1 can modify or destroy data

11 read-only

12 tools total

Community server · catalogue entry verified 05/07/2026

How to control MCP Server for Apache Airflow ↓

TOOL MAP

What MCP Server for Apache Airflow exposes to your agents

Read (11) Write / Execute (1) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous MCP Server for Apache Airflow tools

Execute · High airflow_trigger_dag This tool initiates execution of external workflows whose effects depend on the DAG's configuration and tasks.

1 of MCP Server for Apache Airflow's 12 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control MCP Server for Apache Airflow

PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Server for Apache Airflow, and nothing reaches the server without passing your rules. These are the rules we recommend:

Cap read operations

{
  "airflow_get_dag": {
    "limits": [
      {
        "counter": "airflow_get_dag_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register MCP Server for Apache Airflow — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON MCP SERVER FOR APACHE AIRFLOW →

Instant setup, no code required.

FULL CATALOGUE

All 12 MCP Server for Apache Airflow tools

EXECUTE 1 tools

Execute airflow_trigger_dag Trigger a DAG run

READ 11 tools

Read airflow_get_dag Get details of a specific DAG Read airflow_get_dag_run Get details of a specific DAG run Read airflow_get_dag_run_logs Get logs for all tasks in a DAG run Read airflow_get_task_instance Get details of a specific task instance Read airflow_get_task_logs Get logs for a specific task instance Read airflow_list_dag_runs List DAG runs for a specific DAG Read airflow_list_dags List all DAGs in Airflow Read airflow_list_task_instances List task instances for a DAG run Read airflow_pause_dag Pause a DAG Read airflow_tail_dag_run Tail/monitor a DAG run showing recent activity and logs Read airflow_unpause_dag Unpause a DAG

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about MCP Server for Apache Airflow

Is the MCP Server for Apache Airflow MCP server safe to use without restrictions? +

The MCP Server for Apache Airflow server is primarily read-only with 11 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the MCP Server for Apache Airflow MCP server expose? +

12 tools across 2 categories: Execute, Read. 11 are read-only. 1 can modify, create, or delete data.

How do I enforce a policy on MCP Server for Apache Airflow? +

Register the MCP Server for Apache Airflow MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every MCP Server for Apache Airflow tool call.

Deterministic rules across all 12 MCP Server for Apache Airflow tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP SERVER FOR APACHE AIRFLOW →

Instant setup, no code required.

12 MCP Server for Apache Airflow tools catalogued and risk-classified — across an index of 43,000+ MCP servers.