Medium Risk

add_items_to_collection

Add one or more items to a collection by their item keys.

How to control add_items_to_collection ↓

What add_items_to_collection does on Zotero

AI agents use add_items_to_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.

Medium Risk

Why add_items_to_collection needs a policy

The tool modifies a collection by adding items to it, which is a reversible write operation. This is not destructive (items and collections remain intact), not financial, and not execute-level (no code/command execution). Severity is medium because misuse could corrupt research library organization or add irrelevant items to collections, but the operation is fully reversible by removing items afterward.

From the tool's definition Tool description states 'Add one or more items to a collection' – a create/modify operation that adds items to an existing collection without removing or destroying data.

Documented attack patterns abuse exactly the kind of access add_items_to_collection gives an agent:

How to control add_items_to_collection

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 add_items_to_collection:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "add_items_to_collection": {
      "limits": [
        {
          "counter": "add_items_to_collection_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

add_items_to_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.

  1. Create a free account and register Zotero — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about add_items_to_collection

What does the add_items_to_collection tool do? +

Add one or more items to a collection by their item keys. 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.

How do I enforce a policy on add_items_to_collection? +

Register the Zotero MCP server in PolicyLayer and add a rule for add_items_to_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.

What risk level is add_items_to_collection? +

add_items_to_collection is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit add_items_to_collection? +

Yes. Add a rate_limit block to the add_items_to_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.

How do I block add_items_to_collection completely? +

Set action: deny in the PolicyLayer policy for add_items_to_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.

What MCP server provides add_items_to_collection? +

add_items_to_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.

Enforce policy on every Zotero tool call.

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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.