browser_execute_script · Playwright MCP Server MCP

WHAT IT DOES

What browser_execute_script does on Playwright MCP Server

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

This tool allows running arbitrary JavaScript in a browser context, which is a classic Execute operation. While JavaScript execution itself is not inherently destructive, it can be used to perform side effects (navigate, click, submit forms, exfiltrate data, modify page state) depending on the script argument.

From the tool's definition Tool name contains 'execute_script' and description states 'Execute custom JavaScript code in the browser context.' This directly enables execution of arbitrary code within a browser environment.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_execute_script Rate-limited

browser_execute_script 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_execute_script": {
      "limits": [
        {
          "counter": "browser_execute_script_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 Server, so you can run agents against it safely.

FAQ

Questions about browser_execute_script

What does the browser_execute_script tool do? +

Execute custom JavaScript code in the browser context. Returns the result of the script execution. It is categorised as a Execute tool in the Playwright 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 browser_execute_script? +

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

What risk level is browser_execute_script? +

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

Can I rate-limit browser_execute_script? +

Yes. Add a rate_limit block to the browser_execute_script 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_execute_script completely? +

Set action: deny in the PolicyLayer policy for browser_execute_script. 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_execute_script? +

browser_execute_script is provided by the Playwright MCP Server MCP server (leviathangk/playwrightmcpforcrawler). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.