Delete a dashboard.
AI agents call delete_dashboard to permanently remove resources in Metabase Mcp Navi — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a dashboard is an irreversible action that destroys data and cannot be undone. This fits the Destructive category definition. Severity is high because a dashboard may contain important queries, visualizations, and configuration that multiple users depend on, and its loss could disrupt analytics workflows. Confidence is high because the intent is unambiguous from both name and description.
From the tool's definition Tool name is 'delete_dashboard' and description states 'Delete a dashboard.' The verb 'delete' is explicit and permanent.
Attacks that exploit this kind of access
Delete a dashboard. It is categorised as a Destructive tool in the Metabase Mcp Navi MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Metabase Mcp Navi MCP server in PolicyLayer and add a rule for delete_dashboard: 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 Navi. Nothing to install.
delete_dashboard 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_dashboard 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_dashboard. 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_dashboard is provided by the Metabase Mcp Navi MCP server (manish-coder-1007/metabase-mcp-navi). 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 →