Delete saved searches by key.
AI agents call delete_saved_search 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 tool permanently removes saved searches, which cannot be automatically recovered. While the blast radius is confined to search configuration (not core data loss like items or attachments), deletion of saved searches represents an irreversible modification that could disrupt a user's research workflow.
From the tool's definition Tool name explicitly contains 'delete' and description states 'Delete saved searches by key' — irreversible removal of user-configured search queries.
Attacks that exploit this kind of access
Delete saved searches by key. 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_saved_search: 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_saved_search 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_saved_search 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_saved_search. 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_saved_search 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 →