index_items · Mcp Zotero MCP: Risk & Policy

WHAT IT DOES

What index_items does on Mcp Zotero

AI agents invoke index_items to trigger actions in Mcp Zotero. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why index_items needs a policy

Indexing involves executing a computational process (generating embeddings, writing index data) rather than simply reading or writing user-facing data. It triggers external operations (local embedding pipeline) and modifies index state, making Execute the most appropriate category. Severity is medium as misuse could cause unintended processing or resource consumption but is not irreversible.

From the tool's definition "Index specific Zotero items by their keys" — indexing implies processing/embedding items (likely generating local embeddings for semantic search as mentioned in server description), which is an active operation with side effects beyond simple data retrieval.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

index_items Rate-limited

index_items stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "index_items": {
      "limits": [
        {
          "counter": "index_items_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about index_items

What does the index_items tool do? +

Index specific Zotero items by their keys. It is categorised as a Execute tool in the Mcp Zotero MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on index_items? +

Register the Mcp Zotero MCP server in PolicyLayer and add a rule for index_items: 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 Mcp Zotero. Nothing to install.

What risk level is index_items? +

index_items is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit index_items? +

Yes. Add a rate_limit block to the index_items 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 index_items completely? +

Set action: deny in the PolicyLayer policy for index_items. 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 index_items? +

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