generate_screen_from_text · Stitch- MCP: Risk & Policy

WHAT IT DOES

What generate_screen_from_text does on Stitch-MCP

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

WHY IT NEEDS A POLICY

Why generate_screen_from_text needs a policy

The tool generates screens (creates new design artifacts) within a project, which is a reversible write operation. While the description is empty, the naming pattern and sibling tools ('edit_screens', 'get_screen') establish this as a screen creation capability. This is Write rather than Execute because it creates domain-specific design objects rather than executing arbitrary code.

From the tool's definition Tool name 'generate_screen_from_text' and context as part of Google Stitch's 'screen generation/editing' capabilities suggests creation of new design artifacts.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

generate_screen_from_text Rate-limited

generate_screen_from_text 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_screen_from_text": {
      "limits": [
        {
          "counter": "generate_screen_from_text_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 Stitch-MCP, so you can run agents against it safely.

FAQ

Questions about generate_screen_from_text

What does the generate_screen_from_text tool do? +

generate_screen_from_text. It is categorised as a Write tool in the Stitch-MCP 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_screen_from_text? +

Register the Stitch- MCP server in PolicyLayer and add a rule for generate_screen_from_text: 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 Stitch-MCP. Nothing to install.

What risk level is generate_screen_from_text? +

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

Can I rate-limit generate_screen_from_text? +

Yes. Add a rate_limit block to the generate_screen_from_text 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_from_text completely? +

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

generate_screen_from_text is provided by the Stitch- MCP server (samueljayasingh/stitchmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.