index_library · Mcp Zotero MCP: Risk & Policy

WHAT IT DOES

What index_library does on Mcp Zotero

AI agents invoke index_library 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_library needs a policy

index_library executes an indexing process rather than simply reading or writing data. It triggers semantic search index generation from PDFs via local embeddings, which is a computational operation that modifies system state (the index itself). While not destructive or financial, it clearly executes external processes.

From the tool's definition Tool performs 'build or update' operations on a semantic search index, which involves running computational processes (embedding generation, index construction) whose effects depend on which library/collection is indexed.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

index_library Rate-limited

index_library 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_library": {
      "limits": [
        {
          "counter": "index_library_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_library

What does the index_library tool do? +

Build or update the semantic search index from Zotero library or collection. 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_library? +

Register the Mcp Zotero MCP server in PolicyLayer and add a rule for index_library: 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_library? +

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

Can I rate-limit index_library? +

Yes. Add a rate_limit block to the index_library 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_library completely? +

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

index_library 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.