delete_record
AI agents call delete_record to permanently remove resources in Enterprise MCP Template — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool name 'delete_record' explicitly indicates deletion of data, which is irreversible and destructive. Despite the empty description, the semantic meaning is unambiguous. In an enterprise context with upstream systems like Salesforce, deleting records has significant blast radius.
From the tool's definition Tool name is 'delete_record' with no description provided. The name itself indicates irreversible deletion of data records.
Attacks that exploit this kind of access
delete_record. It is categorised as a Destructive tool in the Enterprise MCP Template MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Enterprise 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 Enterprise 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 Enterprise MCP Template MCP server (victor-velazquez-ai/enterprise-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 →