runtime_evaluate · Js Reverse MCP: Risk & Policy

WHAT IT DOES

What runtime_evaluate does on Js Reverse

AI agents invoke runtime_evaluate to trigger actions in Js Reverse. 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 runtime_evaluate needs a policy

This tool executes arbitrary JavaScript in a browser page context, which can perform any action the page can: read/write DOM, submit forms, trigger logins, exfiltrate data, or invoke APIs. The effects depend entirely on the code passed as arguments, making it Execute category. Severity is high because an AI agent could use it to perform unauthorized actions, extract credentials, or manipulate web applications.

From the tool's definition 在页面上下文中执行JavaScript代码（可用于填写表单、触发登录等）— 'execute JavaScript code in page context'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

runtime_evaluate Rate-limited

runtime_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": {
    "runtime_evaluate": {
      "limits": [
        {
          "counter": "runtime_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 Js Reverse, so you can run agents against it safely.

FAQ

Questions about runtime_evaluate

What does the runtime_evaluate tool do? +

在页面上下文中执行JavaScript代码（可用于填写表单、触发登录等）. It is categorised as a Execute tool in the Js Reverse MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on runtime_evaluate? +

Register the Js Reverse MCP server in PolicyLayer and add a rule for runtime_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 Js Reverse. Nothing to install.

What risk level is runtime_evaluate? +

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

Can I rate-limit runtime_evaluate? +

Yes. Add a rate_limit block to the runtime_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 runtime_evaluate completely? +

Set action: deny in the PolicyLayer policy for runtime_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 runtime_evaluate? +

runtime_evaluate is provided by the Js Reverse MCP server (jenn619/js-reverse-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.