runtime_call_function · Js Reverse MCP: Risk & Policy

WHAT IT DOES

What runtime_call_function does on Js Reverse

AI agents invoke runtime_call_function 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_call_function needs a policy

This tool executes arbitrary JavaScript functions within a browser page context. An AI agent could misuse it to invoke any global function with attacker-controlled arguments, triggering unintended side effects, exfiltrating data, or manipulating page state. The tool is part of a JS reverse engineering/CTF toolkit that operates within a live browser, increasing the blast radius.

From the tool's definition 调用页面中的指定全局函数，传入参数并获取返回值 — calls a specified global function in the page with given arguments and retrieves return values

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

runtime_call_function Rate-limited

runtime_call_function 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_call_function": {
      "limits": [
        {
          "counter": "runtime_call_function_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_call_function

What does the runtime_call_function tool do? +

调用页面中的指定全局函数，传入参数并获取返回值. 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_call_function? +

Register the Js Reverse MCP server in PolicyLayer and add a rule for runtime_call_function: 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_call_function? +

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

Can I rate-limit runtime_call_function? +

Yes. Add a rate_limit block to the runtime_call_function 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_call_function completely? +

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

runtime_call_function 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.