List DAG runs for a specific DAG
AI agents call airflow_list_dag_runs to retrieve information from MCP Server for Apache Airflow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries historical DAG run data from Airflow's REST API. It performs no creation, modification, deletion, or execution of workflows. The blast radius is minimal—an AI agent misusing this tool could only over-query the API or leak information about DAG runs, not cause operational damage or data loss.
From the tool's definition Tool name 'airflow_list_dag_runs' and description 'List DAG runs for a specific DAG' indicate a read-only operation that retrieves and displays information about DAG run history without modifying any state.
Attacks that exploit this kind of access
List DAG runs for a specific DAG. It is categorised as a Read tool in the MCP Server for Apache Airflow MCP Server, which means it retrieves data without modifying state.
Register the MCP Server for Apache Airflow MCP server in PolicyLayer and add a rule for airflow_list_dag_runs: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches MCP Server for Apache Airflow. Nothing to install.
airflow_list_dag_runs is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the airflow_list_dag_runs rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for airflow_list_dag_runs. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
airflow_list_dag_runs is provided by the MCP Server for Apache Airflow MCP server (tomnagengast/mcp-server-airflow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →