AI agents call search to retrieve information from ZotSeek 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 from the user's Zotero library using semantic search. It has no side effects—it does not create, modify, delete, or execute external operations. It is a read-only retrieval mechanism. The 'local and private' nature indicates data remains on the user's system, further supporting a low-severity read operation.
From the tool's definition Tool name is 'search' and description indicates 'Semantic search over the user' (presumably over user's Zotero library). The verb 'search' and context of 'find papers by meaning' indicate a query/retrieval operation with no modification of data.
Attacks that exploit this kind of access
Semantic search over the user. It is categorised as a Read tool in the ZotSeek MCP Server, which means it retrieves data without modifying state.
Register the ZotSeek MCP server in PolicyLayer and add a rule for 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 ZotSeek. Nothing to install.
search 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 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. 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 is provided by the ZotSeek MCP server (introfini/ZotSeek). 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 →