AI agents call zemax_merit_value to retrieve information from Zemax without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only reads and returns the current merit function value from the optical design. It has no side effects, does not modify any data, and is purely a query/retrieval operation.
From the tool's definition Return the current merit function value (lower is better)
Attacks that exploit this kind of access
Return the current merit function value (lower is better). It is categorised as a Read tool in the Zemax MCP Server, which means it retrieves data without modifying state.
Register the Zemax MCP server in PolicyLayer and add a rule for zemax_merit_value: 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.
zemax_merit_value is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the zemax_merit_value 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.
Set action: deny in the PolicyLayer policy for zemax_merit_value. 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.
zemax_merit_value 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.
zemax_merit_value 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 →