cloak_evaluate · CloakBrowser MCP Server MCP: Risk & Policy

WHAT IT DOES

What cloak_evaluate does on CloakBrowser MCP Server

AI agents invoke cloak_evaluate to trigger actions in CloakBrowser MCP Server. 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 cloak_evaluate needs a policy

This tool executes arbitrary JavaScript in the browser page context, which can perform virtually any action including reading/writing data, making network requests, manipulating the DOM, accessing cookies/localStorage, and triggering side effects. Arbitrary code execution in a browser context has high blast radius.

From the tool's definition Evaluate JavaScript expression in the page context

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cloak_evaluate Rate-limited

cloak_evaluate 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": {
    "cloak_evaluate": {
      "limits": [
        {
          "counter": "cloak_evaluate_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 CloakBrowser MCP Server, so you can run agents against it safely.

FAQ

Questions about cloak_evaluate

What does the cloak_evaluate tool do? +

Evaluate JavaScript expression in the page context. It is categorised as a Execute tool in the CloakBrowser MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on cloak_evaluate? +

Register the CloakBrowser MCP Server MCP server in PolicyLayer and add a rule for cloak_evaluate: 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 CloakBrowser MCP Server. Nothing to install.

What risk level is cloak_evaluate? +

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

Can I rate-limit cloak_evaluate? +

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

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

cloak_evaluate is provided by the CloakBrowser MCP Server MCP server (miwoomiwoo/cloakbrowser-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.