Remove a product from a bundle/set
AI agents call remove_product_from_bundle to permanently remove resources in Upmind MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a product from a bundle destroys the relationship between the product and the bundle. This action is not easily reversible without knowing the prior state, and could disrupt customer-facing offerings or active subscriptions tied to the bundle configuration. Given the financial context of an e-commerce/product management platform, the blast radius is high.
From the tool's definition 'Remove a product from a bundle/set' - removing a product from a bundle is an irreversible deletion of that association
Attacks that exploit this kind of access
Remove a product from a bundle/set. It is categorised as a Destructive tool in the Upmind MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Upmind MCP Server MCP server in PolicyLayer and add a rule for remove_product_from_bundle: 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 Upmind MCP Server. Nothing to install.
remove_product_from_bundle 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_product_from_bundle 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_product_from_bundle. 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_product_from_bundle is provided by the Upmind MCP Server MCP server (stardeltapower/upmind-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 →