AI agents call get_saved_searches to retrieve information from Zotero without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves metadata about saved searches in Zotero—it performs a read-only operation that returns configuration data without side effects. No data is created, modified, deleted, or executed. The blast radius of misuse is minimal, as an agent could only view search definitions that already exist in the library.
From the tool's definition Tool name 'get_saved_searches' and description 'Get saved searches (smart collections) defined in the Zotero library. Returns search names and their filter conditions.' indicate a retrieval operation with no modification or deletion of data.
Attacks that exploit this kind of access
Get saved searches (smart collections) defined in the Zotero library. Returns search names and their filter conditions. It is categorised as a Read tool in the Zotero MCP Server, which means it retrieves data without modifying state.
Register the Zotero MCP server in PolicyLayer and add a rule for get_saved_searches: 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. Nothing to install.
get_saved_searches 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 get_saved_searches 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 get_saved_searches. 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.
get_saved_searches is provided by the Zotero MCP server (xbghc/zotero-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 →