Remove saved credentials. You
AI agents call vitrine_logout to permanently remove resources in Vitrine MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing saved credentials is a destructive, non-reversible action: the stored credentials are deleted and the session is terminated. While not the highest blast radius (credentials can be re-entered), an AI agent misusing this tool would break all subsequent authenticated operations, making it effectively disruptive and irreversible without manual re-authentication.
From the tool's definition 'Remove saved credentials' — irreversibly deletes stored authentication credentials
Attacks that exploit this kind of access
Remove saved credentials. You. It is categorised as a Destructive tool in the Vitrine MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Vitrine MCP Server MCP server in PolicyLayer and add a rule for vitrine_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 Vitrine MCP Server. Nothing to install.
vitrine_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 vitrine_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 vitrine_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.
vitrine_logout is provided by the Vitrine MCP Server MCP server (vitrine3d/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 →