vibe_design · VibeServe MCP: Risk & Policy

WHAT IT DOES

What vibe_design does on VibeServe

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

WHY IT NEEDS A POLICY

Why vibe_design needs a policy

The tool creates new UI code (a landing page), which is a Write operation. It produces/generates artifacts rather than reading existing data or executing arbitrary commands. Severity is medium because it could generate and potentially deploy production UI code, but it appears to be a code generation step rather than a direct deployment action.

From the tool's definition Generate a landing page using curated DESIGN.md templates

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

vibe_design Rate-limited

vibe_design 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": {
    "vibe_design": {
      "limits": [
        {
          "counter": "vibe_design_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 VibeServe, so you can run agents against it safely.

FAQ

Questions about vibe_design

What does the vibe_design tool do? +

Generate a landing page using curated DESIGN.md templates. It is categorised as a Write tool in the VibeServe MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on vibe_design? +

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

What risk level is vibe_design? +

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

Can I rate-limit vibe_design? +

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

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

vibe_design is provided by the VibeServe MCP server (ncsound919/vibeserve). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.