AI agents call get_recent_items 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.
The tool queries and returns data from the Zotero library without creating, modifying, or deleting anything. It is purely informational retrieval, matching the Read category definition of 'retrieves or queries data; no side effects'.
From the tool's definition Tool description states it 'Get[s] the most recently added items in the Zotero library' and 'Returns items sorted by dateAdded in descending order.' This is a retrieval operation with no modifications or side effects.
Attacks that exploit this kind of access
Get the most recently added items in the Zotero library. Useful for checking what was recently imported or created. Returns items sorted by dateAdded in descending order. 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_recent_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. Nothing to install.
get_recent_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 get_recent_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 get_recent_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.
get_recent_items 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 →