Delete a Metabase question (card).
AI agents call delete_card to permanently remove resources in Metabase MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes a Metabase card (saved question), which cannot be undone. Deletion is irreversible data destruction. While the blast radius is scoped to a single card and not system-wide, the action itself is destructive. This is more severe than Write or Execute because it eliminates data rather than just modifying or executing it.
From the tool's definition Tool name is 'delete_card' with description 'Delete a Metabase question (card).' The verb 'delete' and the action of removing a card are irreversible operations that destroy data.
Attacks that exploit this kind of access
Delete a Metabase question (card). It is categorised as a Destructive tool in the Metabase MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Metabase MCP Server MCP server in PolicyLayer and add a rule for delete_card: 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 Metabase MCP Server. Nothing to install.
delete_card 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_card 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_card. 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_card is provided by the Metabase MCP Server MCP server (traghav/metabase-server). 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 →