browser_evaluate · Playwright MCP: Risk & Policy

WHAT IT DOES

What browser_evaluate does on Playwright MCP

AI agents invoke browser_evaluate to trigger actions in Playwright 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 browser_evaluate needs a policy

In Playwright, 'evaluate' refers to executing arbitrary JavaScript code within the browser page context. This is an Execute-category action with critical severity because an AI agent could run any JavaScript, enabling data exfiltration, DOM manipulation, credential theft, or triggering destructive actions.

From the tool's definition Tool name 'browser_evaluate' on a Playwright MCP server strongly implies JavaScript evaluation/execution in the browser context, consistent with Playwright's `page.evaluate()` API

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_evaluate Rate-limited

browser_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": {
    "browser_evaluate": {
      "limits": [
        {
          "counter": "browser_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 Playwright MCP, so you can run agents against it safely.

FAQ

Questions about browser_evaluate

What does the browser_evaluate tool do? +

browser_evaluate. It is categorised as a Execute tool in the Playwright 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 browser_evaluate? +

Register the Playwright MCP server in PolicyLayer and add a rule for browser_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 Playwright MCP. Nothing to install.

What risk level is browser_evaluate? +

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

Can I rate-limit browser_evaluate? +

Yes. Add a rate_limit block to the browser_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 browser_evaluate completely? +

Set action: deny in the PolicyLayer policy for browser_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 browser_evaluate? +

browser_evaluate is provided by the Playwright MCP server (roshan571/playwright-mcp2). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.