imugi_iterate · Imugi MCP: Risk & Policy

WHAT IT DOES

What imugi_iterate does on Imugi

AI agents invoke imugi_iterate to trigger actions in Imugi. 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 imugi_iterate needs a policy

imugi_iterate executes a multi-step verification operation (screenshot capture, comparison, analysis generation) whose effects depend on the current state of the page being monitored. While it does not modify code directly, it triggers backend processes that analyze and report on frontend state.

From the tool's definition The tool 'run one iteration' of a verification loop that 'captures a screenshot' and 'compares' against a design, returning 'detailed analysis with scores, heatmap, and fix suggestions.' The use of 'run' indicates execution, and the workflow context shows…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

imugi_iterate Rate-limited

imugi_iterate 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": {
    "imugi_iterate": {
      "limits": [
        {
          "counter": "imugi_iterate_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 Imugi, so you can run agents against it safely.

FAQ

Questions about imugi_iterate

What does the imugi_iterate tool do? +

Run one iteration of the design verification loop: captures a screenshot of your running page, compares it against the design image, and returns a detailed analysis with scores, heatmap, and fix suggestions. IMPORTANT — Workflow for AI editors (Claude Code, Cursor, etc.): 1. Generate or patch the frontend code based on the design image. 2. Call imugi_iterate to verify the result. 3. If the status is. It is categorised as a Execute tool in the Imugi MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on imugi_iterate? +

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

What risk level is imugi_iterate? +

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

Can I rate-limit imugi_iterate? +

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

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

imugi_iterate is provided by the Imugi MCP server (m00n7682/imugi). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.