Remove vehicle from specified portals
AI agents call unpublish_vehicle to permanently remove resources in StockSpark MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Unpublishing a vehicle from portals is an irreversible external action that removes public-facing listings. While the underlying vehicle record may remain in the system, the act of removing from portals affects live customer-facing inventory and may be difficult to undo quickly, especially across multiple third-party portals.
From the tool's definition 'Remove vehicle from specified portals' — the action removes/unpublishes a vehicle listing from external portals
Attacks that exploit this kind of access
Remove vehicle from specified portals. It is categorised as a Destructive tool in the StockSpark MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the StockSpark MCP Server MCP server in PolicyLayer and add a rule for unpublish_vehicle: 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 StockSpark MCP Server. Nothing to install.
unpublish_vehicle 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 unpublish_vehicle 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 unpublish_vehicle. 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.
unpublish_vehicle is provided by the StockSpark MCP Server MCP server (loukach/stockspark-mcp-poc). 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 →