Remove an item from the inventory.
AI agents call homebox_delete_item to permanently remove resources in Homebox MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes inventory items with no documented undo mechanism. Deletion is irreversible and represents data loss. Although the blast radius is scoped to a single inventory item (not system-wide), unauthorized or erroneous deletions could corrupt the inventory database.
From the tool's definition Tool name contains 'delete' and description states 'Remove an item from the inventory' — irreversible deletion of data.
Attacks that exploit this kind of access
Remove an item from the inventory. It is categorised as a Destructive tool in the Homebox MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Homebox MCP Server MCP server in PolicyLayer and add a rule for homebox_delete_item: 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 Homebox MCP Server. Nothing to install.
homebox_delete_item 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 homebox_delete_item 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 homebox_delete_item. 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.
homebox_delete_item is provided by the Homebox MCP Server MCP server (oangelo/homebox-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 →