AI agents call nworks_logout to permanently remove resources in Nworks — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes all stored NAVER WORKS authentication credentials and tokens. While it does not delete user data or files, it permanently removes the authentication state, which would immediately disrupt all AI agent operations on the NAVER WORKS platform and cannot be undone without re-authenticating. The word '삭제' (delete) confirms destructive, irreversible action.
From the tool's definition 인증 정보와 토큰을 모두 삭제합니다 (deletes all stored authentication credentials and tokens)
Documented attack patterns abuse exactly the kind of access nworks_logout gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Nworks, and nothing reaches the server without passing your rules. This is the rule we recommend for nworks_logout:
{
"version": "1",
"default": "deny",
"hide": [
"nworks_logout"
]
} nworks_logout 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.
저장된 NAVER WORKS 인증 정보와 토큰을 모두 삭제합니다. It is categorised as a Destructive tool in the Nworks MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Nworks MCP server in PolicyLayer and add a rule for nworks_logout: 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 Nworks. Nothing to install.
nworks_logout 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 nworks_logout 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 nworks_logout. 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.
nworks_logout is provided by the Nworks MCP server (yjcho9317/nworks). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Nworks, 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.
26 Nworks tools catalogued and risk-classified — across an index of 43,000+ MCP servers.