AI agents call delete_dataset_metric to permanently remove resources in Superset — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool performs deletion, which is an irreversible operation that cannot be undone. This places it in the Destructive category. The severity is high because deleting metrics could break dependent charts, dashboards, and analytical queries that rely on those metrics, impacting multiple users and analyses. The confidence is high based on explicit 'delete' terminology and clear destructive intent.
From the tool's definition Tool name 'delete_dataset_metric' and description 'Delete one or more metrics from a dataset' indicate irreversible deletion of metrics.
Documented attack patterns abuse exactly the kind of access delete_dataset_metric gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Superset, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_dataset_metric:
{
"version": "1",
"default": "deny",
"hide": [
"delete_dataset_metric"
]
}delete_dataset_metric disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Delete one or more metrics from a dataset. It is categorised as a Destructive tool in the Superset MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Superset MCP server in PolicyLayer and add a rule for delete_dataset_metric: 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 Superset. Nothing to install.
delete_dataset_metric is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the delete_dataset_metric 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 delete_dataset_metric. 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.
delete_dataset_metric is provided by the Superset MCP server (winding2020/superset-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Superset, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
31 Superset tools catalogued and risk-classified — across an index of 43,000+ MCP servers.