generate_screen · Mockit MCP: Risk & Policy

WHAT IT DOES

What generate_screen does on Mockit

AI agents invoke generate_screen to trigger actions in Mockit. 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 generate_screen needs a policy

This tool executes a multi-step pipeline: it invokes an LLM (Claude) to generate HTML and then runs a Playwright headless browser to render and screenshot it. This constitutes executing external processes and browser automation, not merely reading or writing data. Misuse could result in arbitrary code execution within the headless browser context or unexpected API usage/costs.

From the tool's definition 'Generate a premium iOS mobile UI mockup' using 'Claude + a Playwright headless renderer' — triggers external operations including running a headless browser (Playwright) and potentially invoking Claude CLI or Anthropic API

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

generate_screen Rate-limited

generate_screen 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": {
    "generate_screen": {
      "limits": [
        {
          "counter": "generate_screen_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 Mockit, so you can run agents against it safely.

FAQ

Questions about generate_screen

What does the generate_screen tool do? +

Generate a premium iOS mobile UI mockup from a text brief. Outputs both the screenshot (PNG) and the underlying HTML. Use this when the user asks to design, mock up, or visualize a mobile app screen. It is categorised as a Execute tool in the Mockit MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on generate_screen? +

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

What risk level is generate_screen? +

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

Can I rate-limit generate_screen? +

Yes. Add a rate_limit block to the generate_screen 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_screen completely? +

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

generate_screen is provided by the Mockit MCP server (karyaboyraz/mockit-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.