Retrieve deleted items (requires since).
AI agents call deleted_items to retrieve information from Mcp Zotero without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries data about items that have already been deleted from the Zotero library. It performs no side effects, creates no modifications, and cannot undo or alter state. It is purely informational retrieval of metadata about past deletions. The severity is low because accessing deletion history poses minimal risk—it is read-only access to existing records.
From the tool's definition Tool name 'deleted_items' and description 'Retrieve deleted items' indicate a query/retrieval operation with no modification or destructive capability. The 'requires since' parameter is a filter for fetching, not a destructive action.
Attacks that exploit this kind of access
Retrieve deleted items (requires since). It is categorised as a Read tool in the Mcp Zotero MCP Server, which means it retrieves data without modifying state.
Register the Mcp Zotero MCP server in PolicyLayer and add a rule for deleted_items: 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.
deleted_items is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the deleted_items 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 deleted_items. 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.
deleted_items 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 →