Zotero Assistant

15 tools. 6 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated:

6 can modify or destroy data
9 read-only
15 tools total

Community server · catalogue entry verified 30/06/2026

How to control Zotero Assistant ↓

What Zotero Assistant exposes to your agents

Read (9) Write / Execute (5) Destructive / Financial (1)
Critical Risk

The most dangerous Zotero Assistant tools

6 of Zotero Assistant's 15 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Zotero Assistant

PolicyLayer is an MCP gateway — it sits between your AI agents and Zotero Assistant, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations
{
  "trash_item": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations
{
  "attach": {
    "limits": [
      {
        "counter": "attach_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "get_collection_items": {
    "limits": [
      {
        "counter": "get_collection_items_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register Zotero Assistant — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON ZOTERO ASSISTANT →

Instant setup, no code required.

All 15 Zotero Assistant tools

Questions about Zotero Assistant

Can an AI agent delete data through the Zotero Assistant MCP server? +

Yes. The Zotero Assistant server exposes 1 destructive tools including trash_item. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Zotero Assistant? +

The Zotero Assistant server has 5 write tools including attach, create_collection, create_note. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Zotero Assistant.

How many tools does the Zotero Assistant MCP server expose? +

15 tools across 2 categories: Read, Write. 9 are read-only. 6 can modify, create, or delete data.

How do I enforce a policy on Zotero Assistant? +

Register the Zotero Assistant MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Zotero Assistant tool call.

Deterministic rules across all 15 Zotero Assistant tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

15 Zotero Assistant 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.