select_frame · JS Reverse MCP: Risk & Policy

WHAT IT DOES

What select_frame does on JS Reverse MCP

AI agents invoke select_frame to trigger actions in JS Reverse MCP. 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 select_frame needs a policy

While selecting a frame is itself a configuration/state-change action, its explicit purpose is to set the execution context for JavaScript execution tools like evaluate_script and hook_function. It directly enables and influences code execution in a browser context, making Execute the most appropriate category. Misuse could redirect script execution into sensitive frames (e.g., payment iframes, auth flows).

From the tool's definition Selects a frame as the execution context for evaluate_script, hook_function, inspect_object, and other tools that run JavaScript in the page

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

select_frame Rate-limited

select_frame 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": {
    "select_frame": {
      "limits": [
        {
          "counter": "select_frame_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 MCP, so you can run agents against it safely.

FAQ

Questions about select_frame

What does the select_frame tool do? +

Selects a frame (by index from list_frames) as the execution context for evaluate_script, hook_function, inspect_object, and other tools that run JavaScript in the page. It is categorised as a Execute tool in the JS Reverse MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on select_frame? +

Register the JS Reverse MCP server in PolicyLayer and add a rule for select_frame: 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 MCP. Nothing to install.

What risk level is select_frame? +

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

Can I rate-limit select_frame? +

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

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

select_frame is provided by the JS Reverse MCP server (noone-hub/jsreverser-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.