Delete all users that match the given name (case-insensitive)
AI agents call delete-user-by-name to permanently remove resources in Users — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly removes user records from the system based on a name match. The case-insensitive matching means a single invocation could delete multiple users unexpectedly if names overlap, making it a destructive operation with potential for broad unintended data loss. The most severe category (Destructive) applies because deletion cannot be undone.
From the tool's definition The tool description explicitly states it "Delete[s] all users that match the given name". The verb "delete" combined with "all users" indicates irreversible removal of data.
Attacks that exploit this kind of access
Delete all users that match the given name (case-insensitive). It is categorised as a Destructive tool in the Users MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Users MCP server in PolicyLayer and add a rule for delete-user-by-name: 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 Users. Nothing to install.
delete-user-by-name 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-user-by-name 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-user-by-name. 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-user-by-name is provided by the Users MCP server (stormdotcom/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 →