install_plugin_from_url · Zotero Agent MCP: Risk & Policy

WHAT IT DOES

What install_plugin_from_url does on Zotero Agent

AI agents invoke install_plugin_from_url 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 install_plugin_from_url needs a policy

This tool downloads and installs arbitrary XPI plugin code into Zotero, which constitutes arbitrary code execution on the host machine. The description explicitly states 'Installing an XPI is arbitrary code execution' — this is the highest-risk Execute action possible, as a malicious or misconfigured URL could install malware, exfiltrate data, or compromise the entire system. The blast radius is critical.

From the tool's definition Installing an XPI is arbitrary code execution — requires eval.enabled. Download and install/upgrade a plugin XPI from an http(s):// or file:// URL

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

install_plugin_from_url Rate-limited

install_plugin_from_url 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": {
    "install_plugin_from_url": {
      "limits": [
        {
          "counter": "install_plugin_from_url_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 install_plugin_from_url

What does the install_plugin_from_url tool do? +

Download and install/upgrade a plugin XPI from an http(s):// or file:// URL reachable FROM the Zotero machine (dev loop). Installing an XPI is arbitrary code execution — requires eval.enabled. Self-upgrade replies first, installs after 500ms. 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 install_plugin_from_url? +

Register the Zotero Agent MCP server in PolicyLayer and add a rule for install_plugin_from_url: 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 install_plugin_from_url? +

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

Can I rate-limit install_plugin_from_url? +

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

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

install_plugin_from_url 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.