runtime_evaluate · CDP-MCP Server MCP: Risk & Policy

WHAT IT DOES

What runtime_evaluate does on CDP-MCP Server

AI agents invoke runtime_evaluate 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 runtime_evaluate needs a policy

This tool executes arbitrary JavaScript in the browser's global page context, giving an AI agent full ability to run any code: exfiltrate data, manipulate the DOM, make network requests, access cookies/localStorage, or trigger any browser API. The blast radius is critical because there are no restrictions on what code can be run.

From the tool's definition Evaluate a JavaScript expression in the global 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 CDP-MCP Server, so you can run agents against it safely.

FAQ

Questions about runtime_evaluate

What does the runtime_evaluate tool do? +

Evaluate a JavaScript expression in the global page context. 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 runtime_evaluate? +

Register the CDP-MCP Server 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 CDP-MCP Server. 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 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.