Remove one or more items from a collection. Items are NOT deleted from the library, only removed from this collection.
AI agents use remove_items_from_collection 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 removes items from a collection but explicitly states they are not deleted from the library. This is a reversible modification (items can be re-added), making it a Write operation rather than Destructive. Misuse could disrupt organization of collections but causes no permanent data loss.
From the tool's definition 'Remove one or more items from a collection. Items are NOT deleted from the library, only removed from this collection.'
Documented attack patterns abuse exactly the kind of access remove_items_from_collection gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Zotero, and nothing reaches the server without passing your rules. This is the rule we recommend for remove_items_from_collection:
{
"version": "1",
"default": "deny",
"tools": {
"remove_items_from_collection": {
"limits": [
{
"counter": "remove_items_from_collection_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} remove_items_from_collection stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Remove one or more items from a collection. Items are NOT deleted from the library, only removed from this collection. 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 remove_items_from_collection: 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.
remove_items_from_collection 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 remove_items_from_collection 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 remove_items_from_collection. 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.
remove_items_from_collection is provided by the Zotero MCP server (zotero-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Zotero, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
27 Zotero tools catalogued and risk-classified — across an index of 43,000+ MCP servers.