Delete a saved Look. This action cannot be undone.
AI agents call delete_look to permanently remove resources in Looker MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool permanently removes a saved Look artifact from Looker. Deletion is irreversible and destroys data that users may depend on for analytics and reporting. While not as critical as deleting entire databases or financial records, this represents a high-severity destructive action that could impact business intelligence and analytics workflows.
From the tool's definition 'Delete a saved Look. This action cannot be undone.' — explicitly states irreversible deletion with no undo capability.
Attacks that exploit this kind of access
Delete a saved Look. This action cannot be undone. It is categorised as a Destructive tool in the Looker MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Looker MCP Server MCP server in PolicyLayer and add a rule for delete_look: 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 Looker MCP Server. Nothing to install.
delete_look 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_look 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_look. 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_look is provided by the Looker MCP Server MCP server (ultrathink-solutions/looker-mcp-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 →