Search the Zotero library by text, tags, type, collection, or date range.
AI agents call search_items to retrieve information from Zotero Assistant without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and filters existing library items based on search criteria. It has no side effects, does not create, modify, or delete data, and does not execute external operations. It is a straightforward read operation that returns search results from the Zotero library.
From the tool's definition Tool name 'search_items' and description explicitly states it 'Search[es] the Zotero library by text, tags, type, collection, or date range' - a pure query operation with no modification or deletion capability.
Attacks that exploit this kind of access
Search the Zotero library by text, tags, type, collection, or date range. It is categorised as a Read tool in the Zotero Assistant MCP Server, which means it retrieves data without modifying state.
Register the Zotero Assistant MCP server in PolicyLayer and add a rule for search_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 Zotero Assistant. Nothing to install.
search_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 search_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 search_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.
search_items 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 →