AI agents use add_item to create or update resources in Zotero — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Zotero environment.
The tool name 'add_item' strongly suggests adding/creating new items to a Zotero library. This is a reversible Write operation. Severity is medium because misuse by an AI agent could pollute a user's bibliography database with unwanted items, but this is not irreversible (items can be deleted) and does not cause financial harm or execute arbitrary code.
From the tool's definition Tool name 'add_item' indicates creation of new data. Sibling tools include 'create_collection', 'delete_item', 'update_item', and 'search_items', suggesting this is a data management system (Zotero bibliography/citation manager).
Attacks that exploit this kind of access
add_item. It is categorised as a Write tool in the Zotero MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Zotero MCP server in PolicyLayer and add a rule for add_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.
add_item is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the add_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 add_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.
add_item is provided by the Zotero MCP server (cr625/zotero-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
add_item is one line of Zotero's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →