design_refine · Pen MCP: Risk & Policy

WHAT IT DOES

What design_refine does on Pen

AI agents invoke design_refine to trigger actions in Pen. 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 design_refine needs a policy

This tool executes automated validation and correction logic on design documents. While it modifies data (the auto-fixes are reversible edits to a design), the primary action is executing a complex validation workflow. The tool's effects depend on the design state and validation rules rather than direct user data specification, placing it in Execute rather than Write.

From the tool's definition Tool performs 'full-tree validation and auto-fixes on a design', indicating it runs automated operations that modify design state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

design_refine Rate-limited

design_refine 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": {
    "design_refine": {
      "limits": [
        {
          "counter": "design_refine_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 Pen, so you can run agents against it safely.

FAQ

Questions about design_refine

What does the design_refine tool do? +

Run full-tree validation and auto-fixes on a design. Part of the layered design workflow. It is categorised as a Execute tool in the Pen MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on design_refine? +

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

What risk level is design_refine? +

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

Can I rate-limit design_refine? +

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

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

design_refine is provided by the Pen MCP server (@zseven-w/pen-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.