ai_analyze_page · Yocoolab MCP: Risk & Policy

WHAT IT DOES

What ai_analyze_page does on Yocoolab

AI agents invoke ai_analyze_page to trigger actions in Yocoolab. 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 ai_analyze_page needs a policy

This tool invokes an external AI service to analyze a web page, which constitutes triggering an external operation. It is not a simple read/query of stored data; it sends a request to an AI backend that may fetch/render the page and run analysis. The most severe applicable category is Execute due to the external operation being triggered.

From the tool's definition "Ask the Yocoolab AI assistant to analyze a web page" and "optional screenshot (vision) and page context" — triggers an external AI operation/request against a live web page

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ai_analyze_page Rate-limited

ai_analyze_page 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": {
    "ai_analyze_page": {
      "limits": [
        {
          "counter": "ai_analyze_page_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 Yocoolab, so you can run agents against it safely.

FAQ

Questions about ai_analyze_page

What does the ai_analyze_page tool do? +

Ask the Yocoolab AI assistant to analyze a web page. Supports text questions with optional screenshot (vision) and page context. Useful for getting AI insights about a page layout, accessibility, or code structure. It is categorised as a Execute tool in the Yocoolab MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on ai_analyze_page? +

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

What risk level is ai_analyze_page? +

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

Can I rate-limit ai_analyze_page? +

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

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

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