Delete a record from a resource
AI agents call delete_record to permanently remove resources in MCP Template — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion of records cannot be undone and represents permanent data loss. This is a core Destructive operation. High severity because an AI agent accidentally calling this tool could cause significant data loss depending on the resource scope and access controls. Confidence is very high given the unambiguous naming and description.
From the tool's definition Tool name is 'delete_record' and description states 'Delete a record from a resource' — explicit language indicating irreversible data removal.
Attacks that exploit this kind of access
Delete a record from a resource. It is categorised as a Destructive tool in the MCP Template MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Template MCP server in PolicyLayer and add a rule for delete_record: 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 Template. Nothing to install.
delete_record 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_record 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_record. 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_record is provided by the MCP Template MCP server (kbhuw/mcp_template). 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 →