Move a note or attachment to trash. Only works on notes/attachments for safety.
AI agents call trash_item to permanently remove resources in Zotero Assistant — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Moving items to trash is a destructive operation that removes data from the active library. While 'trash' may technically allow recovery (unlike permanent deletion), the operation is effectively irreversible from the AI agent's perspective as it cannot be automatically undone, and the tool description does not mention any undo capability.
From the tool's definition Move a note or attachment to trash
Attacks that exploit this kind of access
Move a note or attachment to trash. Only works on notes/attachments for safety. It is categorised as a Destructive tool in the Zotero Assistant MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Zotero Assistant MCP server in PolicyLayer and add a rule for trash_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 Zotero Assistant. Nothing to install.
trash_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 trash_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 trash_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.
trash_item is provided by the Zotero Assistant MCP server (upascal/zotero-assistant-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 →