debugger_evaluate_on_frame · CDP-MCP Server MCP

WHAT IT DOES

What debugger_evaluate_on_frame does on CDP-MCP Server

AI agents invoke debugger_evaluate_on_frame to trigger actions in CDP-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 debugger_evaluate_on_frame needs a policy

This tool executes arbitrary JavaScript code within a paused browser frame via Chrome DevTools Protocol. An AI agent could run any JS expression with full access to the frame's scope, DOM, network APIs, and credentials — enabling data exfiltration, DOM manipulation, credential theft, or further code injection. The blast radius is critical because execution is arbitrary and unconstrained by the caller's intent.

From the tool's definition Evaluate a JavaScript expression in the context of a paused call frame

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

debugger_evaluate_on_frame Rate-limited

debugger_evaluate_on_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": {
    "debugger_evaluate_on_frame": {
      "limits": [
        {
          "counter": "debugger_evaluate_on_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 CDP-MCP Server, so you can run agents against it safely.

FAQ

Questions about debugger_evaluate_on_frame

What does the debugger_evaluate_on_frame tool do? +

Evaluate a JavaScript expression in the context of a paused call frame. It is categorised as a Execute tool in the CDP-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 debugger_evaluate_on_frame? +

Register the CDP-MCP Server MCP server in PolicyLayer and add a rule for debugger_evaluate_on_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 CDP-MCP Server. Nothing to install.

What risk level is debugger_evaluate_on_frame? +

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

Can I rate-limit debugger_evaluate_on_frame? +

Yes. Add a rate_limit block to the debugger_evaluate_on_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 debugger_evaluate_on_frame completely? +

Set action: deny in the PolicyLayer policy for debugger_evaluate_on_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 debugger_evaluate_on_frame? +

debugger_evaluate_on_frame is provided by the CDP-MCP Server MCP server (jekyll-001/cdp-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.