AI agents call delete_record to permanently remove resources in MCP-Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion of records is an irreversible operation that cannot be undone without external backup/recovery mechanisms. This qualifies as Destructive rather than Write (which is reversible). The high severity reflects that an AI agent misusing this tool could permanently remove critical business data from the CRM system.
From the tool's definition Tool name is 'delete_record' and description states 'Delete a record from a specific module'. The verb 'delete' and context of removing a record from a CRM system indicates irreversible data removal.
Documented attack patterns abuse exactly the kind of access delete_record gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP-Server, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_record:
{
"version": "1",
"default": "deny",
"hide": [
"delete_record"
]
}delete_record disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Delete a record from a specific module. It is categorised as a Destructive tool in the MCP-Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP-Server 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-Server. 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-Server MCP server (officehub-tech-llc/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP-Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
9 MCP-Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.