reload_plugin · Zotero Agent MCP: Risk & Policy

WHAT IT DOES

What reload_plugin does on Zotero Agent

AI agents invoke reload_plugin to trigger actions in Zotero Agent. 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 reload_plugin needs a policy

This tool executes a plugin reload operation via the AddonManager, which triggers external runtime operations including restarting the MCP plugin itself and dropping the connection. It requires eval.enabled, indicating it runs arbitrary evaluation.

From the tool's definition 'Reload an installed Zotero plugin via AddonManager', 'Omit addon_id to reload THIS MCP plugin itself', 'Requires eval.enabled'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

reload_plugin Rate-limited

reload_plugin 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": {
    "reload_plugin": {
      "limits": [
        {
          "counter": "reload_plugin_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 Zotero Agent, so you can run agents against it safely.

FAQ

Questions about reload_plugin

What does the reload_plugin tool do? +

Reload an installed Zotero plugin via AddonManager (dev loop). Omit addon_id to reload THIS MCP plugin itself — it replies first, then reloads after 500ms (connection drops briefly). Requires eval.enabled. It is categorised as a Execute tool in the Zotero Agent MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on reload_plugin? +

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

What risk level is reload_plugin? +

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

Can I rate-limit reload_plugin? +

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

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

reload_plugin is provided by the Zotero Agent MCP server (psiQAQ/zotero-agent). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// THE FULL RECORD

reload_plugin is one line of Zotero Agent's registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →