Remove a VIN from the user\
AI agents call remove_saved_vin to permanently remove resources in VIN MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a saved VIN is an irreversible operation that deletes user-stored data. While the blast radius is limited to personal vehicle records (not sensitive financial or operational systems), the operation cannot be undone, meeting the definition of Destructive.
From the tool's definition Tool name 'remove_saved_vin' with action verb 'Remove' indicates deletion of stored data. The description states 'Remove a VIN from the user' (incomplete, but the intent is clear: irreversible deletion of a saved record).
Attacks that exploit this kind of access
Remove a VIN from the user\. It is categorised as a Destructive tool in the VIN MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the VIN MCP server in PolicyLayer and add a rule for remove_saved_vin: 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 VIN MCP. Nothing to install.
remove_saved_vin 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 remove_saved_vin 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 remove_saved_vin. 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.
remove_saved_vin is provided by the VIN MCP server (keptlive/vin-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 →