AI agents call zotero_get_item 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 retrieves bibliographic metadata from the user's local Zotero library indexed by itemKey. It has no side effects, does not execute code, does not modify or delete data, and does not involve financial transactions. The blast radius of misuse is minimal—an agent could only access information already in the user's library without causing harm.
From the tool's definition Tool description states 'Retrieve the details of a specified item' with no modification or deletion capability. The verb 'Retrieve' and the read-only nature of accessing item details confirm this is a query operation.
Attacks that exploit this kind of access
Retrieve the details of a specified item in the Zotero library by itemKey. 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 zotero_get_item: 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.
zotero_get_item 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 zotero_get_item 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 zotero_get_item. 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.
zotero_get_item is provided by the Zotero MCP server (masaki39/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 →