Deactivate a user. The user can no longer sign in but their historical activity is preserved.
AI agents call deactivate_user to permanently remove resources in Kula Ai — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deactivating a user revokes their access permanently (until manually reversed), which is effectively irreversible from an operational standpoint. While historical data is preserved, the action blocks the user from signing in, which constitutes a significant access-revocation action. This is more severe than a simple Write and borders on Destructive since re-enabling requires deliberate remediation.
From the tool's definition Deactivate a user. The user can no longer sign in
Attacks that exploit this kind of access
Deactivate a user. The user can no longer sign in but their historical activity is preserved. It is categorised as a Destructive tool in the Kula Ai MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Kula Ai MCP server in PolicyLayer and add a rule for deactivate_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 Kula Ai. Nothing to install.
deactivate_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 deactivate_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 deactivate_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.
deactivate_user is provided by the Kula Ai MCP server (kula-ai/kula-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 →