chrome_evaluate · Chrome MCP Stealth MCP: Risk & Policy

WHAT IT DOES

What chrome_evaluate does on Chrome MCP Stealth

AI agents invoke chrome_evaluate to trigger actions in Chrome MCP Stealth. 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 chrome_evaluate needs a policy

This tool executes arbitrary JavaScript within a webpage's context, which is a classic Execute pattern - it triggers external operations (JavaScript evaluation) whose effects depend entirely on the arguments provided. While the credential leak scanning is a mitigating control, the core functionality remains code execution with potentially broad side effects.

From the tool's definition Tool name 'chrome_evaluate' combined with description 'Execute JavaScript in page context' indicates arbitrary code execution capability.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

chrome_evaluate Rate-limited

chrome_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": {
    "chrome_evaluate": {
      "limits": [
        {
          "counter": "chrome_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 Chrome MCP Stealth, so you can run agents against it safely.

FAQ

Questions about chrome_evaluate

What does the chrome_evaluate tool do? +

Execute JavaScript in page context. Output scanned for credential leaks. It is categorised as a Execute tool in the Chrome MCP Stealth MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on chrome_evaluate? +

Register the Chrome MCP Stealth MCP server in PolicyLayer and add a rule for chrome_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 Chrome MCP Stealth. Nothing to install.

What risk level is chrome_evaluate? +

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

Can I rate-limit chrome_evaluate? +

Yes. Add a rate_limit block to the chrome_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 chrome_evaluate completely? +

Set action: deny in the PolicyLayer policy for chrome_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 chrome_evaluate? +

chrome_evaluate is provided by the Chrome MCP Stealth MCP server (riaan-fourie/chrome-mcp-stealth). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.