Delete tags.
AI agents call delete_tags 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.
This tool irreversibly removes tags from a Zotero library. While the blast radius is limited to metadata (tags, not entire items or collections), the action cannot be undone through the tool interface. Severity is medium rather than high because tags are metadata artifacts, not primary research data or attachments, and the impact is scoped to organizational metadata rather than data loss.
From the tool's definition Tool name 'delete_tags' explicitly performs deletion. Description states 'Delete tags' with no undo or restoration mechanism described.
Attacks that exploit this kind of access
Delete tags. 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_tags: 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_tags 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_tags 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_tags. 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_tags 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 →