AI agents call get_item_children 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 hierarchical relationships within a Zotero library (child items of a parent item) with no side effects. It aligns with the read-only nature of the server and follows the naming pattern of other query tools (get_item, list_items). The empty description reduces confidence slightly, but the server's explicit read-only designation and sibling context provide strong evidence for the Read category.
From the tool's definition Tool is listed as a sibling on a 'Read-only MCP server' and named 'get_item_children', which retrieves child items associated with a parent item. No modification, deletion, or execution capabilities are described.
Attacks that exploit this kind of access
get_item_children. 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_item_children: 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_item_children 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_item_children 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_item_children. 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_item_children is provided by the Zotero MCP server (nadavweisler/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 →