save_item · Zotero Assistant MCP: Risk & Policy

WHAT IT DOES

What save_item does on Zotero Assistant

AI agents use save_item to create or update resources in Zotero Assistant — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Zotero Assistant environment.

WHY IT NEEDS A POLICY

Why save_item needs a policy

This tool creates new library items with metadata and optional attachments in Zotero. It is reversible (items can be deleted), modifies the library state, and has no financial impact. It falls under Write category rather than Read (retrieval only) or Destructive (irreversible deletion). Severity is medium because misuse could pollute a library with unwanted entries, but the impact is containable and reversible.

From the tool's definition Tool description states 'Create a new item in the Zotero library with metadata and optional attachment.' The verb 'Create' indicates data creation. The ability to add 'optional attachment' suggests file storage operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

save_item Rate-limited

save_item 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "save_item": {
      "limits": [
        {
          "counter": "save_item_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Zotero Assistant, so you can run agents against it safely.

FAQ

Questions about save_item

What does the save_item tool do? +

Create a new item in the Zotero library with metadata and optional attachment. It is categorised as a Write tool in the Zotero Assistant MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on save_item? +

Register the Zotero Assistant MCP server in PolicyLayer and add a rule for save_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 Assistant. Nothing to install.

What risk level is save_item? +

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

Can I rate-limit save_item? +

Yes. Add a rate_limit block to the save_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.

How do I block save_item completely? +

Set action: deny in the PolicyLayer policy for save_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.

What MCP server provides save_item? +

save_item is provided by the Zotero Assistant MCP server (upascal/zotero-assistant-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.