generate_redesign_preview · Fdl MCP: Risk & Policy

WHAT IT DOES

What generate_redesign_preview does on Fdl

AI agents use generate_redesign_preview to create or update resources in Fdl — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Fdl environment.

WHY IT NEEDS A POLICY

Why generate_redesign_preview needs a policy

This tool creates new data (an AI-generated redesign preview) and triggers an external email action as a side effect. It is reversible (the generated preview could be ignored or deleted) and has no destructive or financial impact. It fits the Write category because it creates and delivers a new resource.

From the tool's definition The tool 'generates' a redesign preview and 'returns a confirmation' with an email sent as a side effect. The description states 'Request a free AI-generated redesign preview' and 'the actual preview is emailed within 10 minutes', indicating creation of a new…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

generate_redesign_preview Rate-limited

generate_redesign_preview stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "generate_redesign_preview": {
      "limits": [
        {
          "counter": "generate_redesign_preview_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Fdl, so you can run agents against it safely.

FAQ

Questions about generate_redesign_preview

What does the generate_redesign_preview tool do? +

Request a free AI-generated redesign preview of any website. Returns a confirmation; the actual preview is emailed within 10 minutes. Costs $0. It is categorised as a Write tool in the Fdl MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on generate_redesign_preview? +

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

What risk level is generate_redesign_preview? +

generate_redesign_preview is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit generate_redesign_preview? +

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

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

generate_redesign_preview is provided by the Fdl MCP server (nareshdevelop/fdl-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.