Find items semantically similar to a given item using AI embeddings. Useful for expanding research from a known relevant paper and discovering thematic clusters.
AI agents call find_similar to retrieve information from Zotero Agent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries a semantic similarity index to retrieve related items from the Zotero library. It performs a search operation with no side effects on data — it neither creates, modifies, deletes, nor executes external code. The worst-case misuse is returning irrelevant results to an AI agent, which has minimal blast radius.
From the tool's definition Tool description states 'Find items semantically similar to a given item' and 'discovering thematic clusters' — purely retrieval operations. No modification, deletion, execution, or financial impact described.
Attacks that exploit this kind of access
Find items semantically similar to a given item using AI embeddings. Useful for expanding research from a known relevant paper and discovering thematic clusters. It is categorised as a Read tool in the Zotero Agent MCP Server, which means it retrieves data without modifying state.
Register the Zotero Agent MCP server in PolicyLayer and add a rule for find_similar: 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 Agent. Nothing to install.
find_similar 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 find_similar 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 find_similar. 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.
find_similar is provided by the Zotero Agent MCP server (psiQAQ/zotero-agent). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
find_similar is one line of Zotero Agent's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →