zemax_eval · Zemax MCP: Risk & Policy

WHAT IT DOES

What zemax_eval does on Zemax

AI agents invoke zemax_eval to trigger actions in Zemax. 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 zemax_eval needs a policy

The name 'zemax_eval' contains 'eval', which conventionally means evaluating or executing code/expressions. In the context of an MCP bridge that drives optical designs, this likely executes arbitrary evaluation commands within OpticStudio. However, the description is empty, which reduces confidence.

From the tool's definition Tool name 'zemax_eval' with empty description. The 'eval' suffix strongly suggests code or expression evaluation execution within Zemax OpticStudio.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

zemax_eval Rate-limited

zemax_eval 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": {
    "zemax_eval": {
      "limits": [
        {
          "counter": "zemax_eval_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 Zemax, so you can run agents against it safely.

FAQ

Questions about zemax_eval

What does the zemax_eval tool do? +

zemax_eval. It is categorised as a Execute tool in the Zemax MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on zemax_eval? +

Register the Zemax MCP server in PolicyLayer and add a rule for zemax_eval: 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 Zemax. Nothing to install.

What risk level is zemax_eval? +

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

Can I rate-limit zemax_eval? +

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

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

zemax_eval is provided by the Zemax MCP server (webworn/zemax-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// THE FULL RECORD

zemax_eval is one line of Zemax'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 →