playwright_evaluate

THE RISK

High Risk

Why playwright_evaluate needs a policy

This tool enables execution of arbitrary JavaScript code in a live browser session. While not inherently destructive or financial on its own, it is classified as Execute (highest severity) because: (1) JavaScript execution is a general-purpose code execution primitive, (2) an LLM agent given this tool could inadvertently or maliciously execute code that reads sensitive data, modifies page content, performs…

From the tool's definition Tool performs 'Execute JavaScript in the browser console' which directly runs arbitrary code in a browser context.

Documented attack patterns abuse exactly the kind of access playwright_evaluate gives an agent:

POLICY

How to control playwright_evaluate

PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Playwright CDP, and nothing reaches the server without passing your rules. This is the rule we recommend for playwright_evaluate:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "playwright_evaluate": {
      "limits": [
        {
          "counter": "playwright_evaluate_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

playwright_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.

Create a free account and register MCP Playwright CDP — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More MCP Playwright CDP tools

Destructive playwright_delete Perform an HTTP DELETE request Execute playwright_navigate Navigate to a URL Execute playwright_click Click an element on the page Execute playwright_fill fill out an input field Execute playwright_hover Hover an element on the page Execute playwright_select Select an element on the page with Select tag Write playwright_patch Perform an HTTP PATCH request Write playwright_post Perform an HTTP POST request

All 12 MCP Playwright CDP tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in MCP Playwright CDP → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about playwright_evaluate

What does the playwright_evaluate tool do? +

Execute JavaScript in the browser console. It is categorised as a Execute tool in the MCP Playwright CDP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on playwright_evaluate? +

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

What risk level is playwright_evaluate? +

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

Can I rate-limit playwright_evaluate? +

Yes. Add a rate_limit block to the playwright_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 playwright_evaluate completely? +

Set action: deny in the PolicyLayer policy for playwright_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 playwright_evaluate? +

playwright_evaluate is provided by the MCP Playwright CDP MCP server (lars-hagen/mcp-playwright-cdp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCP Playwright CDP tool call.

Start from MCP Playwright CDP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →