Delete an item.
AI agents call delete_item to permanently remove resources in Mcp Zotero — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The delete_item tool irreversibly removes items from a user's Zotero library. This cannot be undone (Zotero does not provide restore-from-trash for deleted items in standard operation). While the blast radius depends on which item is targeted, deletion of research items, PDFs, or metadata represents permanent data loss.
From the tool's definition Tool name is 'delete_item' with description 'Delete an item.' This directly removes data from Zotero libraries without reversal option.
Attacks that exploit this kind of access
Delete an item. It is categorised as a Destructive tool in the Mcp Zotero MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcp Zotero MCP server in PolicyLayer and add a rule for 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 Mcp Zotero. Nothing to install.
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 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 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.
delete_item is provided by the Mcp Zotero MCP server (nealcaren/mcp-zotero). 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 →