Get details of a specific task instance
AI agents call airflow_get_task_instance 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.
The tool retrieves metadata about a task instance (status, logs, execution history, etc.) without altering any state or triggering any actions. This is purely informational and falls cleanly into the Read category. The blast radius of misuse is minimal — an attacker could gather intelligence about running tasks but cannot modify workflows, trigger executions, or delete data.
From the tool's definition Tool name is 'airflow_get_task_instance' and description states 'Get details of a specific task instance' — this is a retrieval operation with no modification, creation, deletion, or execution of workflows.
Attacks that exploit this kind of access
Get details of a specific task instance. 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_get_task_instance: 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_get_task_instance 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_get_task_instance 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_get_task_instance. 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_get_task_instance 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 →