AI agents use archive_item to create or update resources in Wardrowbe — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Wardrowbe environment.
Archiving is a write operation that changes item metadata or visibility state. It is reversible (items can typically be unarchived), so it does not qualify as Destructive. It has minimal blast radius—hiding a wardrobe item from view is a low-impact data modification action. Severity is low because the effect is scoped to a single item, non-destructive, and easily recoverable.
From the tool's definition Tool description states "Archive item_id (hide from active wardrobe)" — this modifies the state of an item by marking it as archived/hidden, but does not delete it and is reversible.
Attacks that exploit this kind of access
Archive item_id (hide from active wardrobe). Optional reason. It is categorised as a Write tool in the Wardrowbe MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Wardrowbe MCP server in PolicyLayer and add a rule for archive_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 Wardrowbe. Nothing to install.
archive_item is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the archive_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 archive_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.
archive_item is provided by the Wardrowbe MCP server (saya6k/mcp-wardrowbe). 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 →