Remove a specific user or clear the token store
AI agents call clear_user to permanently remove resources in API MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes user records and/or authentication token stores without the ability to undo the action. Deletion of user data is irreversible and represents a destructive operation. The capability to clear the entire token store could affect multiple sessions and is not reversible.
From the tool's definition Tool name is "clear_user" and description states "Remove a specific user or clear the token store" - uses the verb "Remove" and "clear" which indicate irreversible deletion of user data and authentication tokens.
Attacks that exploit this kind of access
Remove a specific user or clear the token store. It is categorised as a Destructive tool in the API MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the API MCP Server MCP server in PolicyLayer and add a rule for clear_user: 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 API MCP Server. Nothing to install.
clear_user 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 clear_user 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 clear_user. 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.
clear_user is provided by the API MCP Server MCP server (vilasone455/api-mcp). 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 →