evaluate_on_callframe · JS Reverse MCP: Risk & Policy

WHAT IT DOES

What evaluate_on_callframe does on JS Reverse MCP

AI agents invoke evaluate_on_callframe 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 evaluate_on_callframe needs a policy

This tool enables execution of arbitrary JavaScript within an active call frame during a debugging session. While the scope is limited to an already-paused context, it allows an AI agent to execute code with access to local variables, scope chain, and potentially sensitive runtime state.

From the tool's definition 'Evaluates a JavaScript expression' and 'execute code in the paused scope' - the tool directly runs arbitrary JavaScript code in a browser debugging context with access to live runtime state and variables.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

evaluate_on_callframe Rate-limited

evaluate_on_callframe 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": {
    "evaluate_on_callframe": {
      "limits": [
        {
          "counter": "evaluate_on_callframe_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 evaluate_on_callframe

What does the evaluate_on_callframe tool do? +

Evaluates a JavaScript expression in the context of a specific call frame while paused. This allows you to inspect variables and execute code in the paused scope. 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 evaluate_on_callframe? +

Register the JS Reverse MCP server in PolicyLayer and add a rule for evaluate_on_callframe: 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 evaluate_on_callframe? +

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

Can I rate-limit evaluate_on_callframe? +

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

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

evaluate_on_callframe 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.