browser_playwright_code · MCP Macaco Playwright MCP

WHAT IT DOES

What browser_playwright_code does on MCP Macaco Playwright

AI agents invoke browser_playwright_code to trigger actions in MCP Macaco Playwright. 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_playwright_code needs a policy

This tool allows arbitrary code execution through Playwright, which can perform any browser automation action including navigation, form submission, file uploads, data exfiltration, credential theft, and triggering unintended side effects. The 'arbitrary' qualifier and lack of constraints make this Execute-level risk.

From the tool's definition Tool name contains 'Execute arbitrary Playwright code directly' and explicitly states it allows 'advanced automation tasks'.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_playwright_code Rate-limited

browser_playwright_code 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_playwright_code": {
      "limits": [
        {
          "counter": "browser_playwright_code_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 MCP Macaco Playwright, so you can run agents against it safely.

FAQ

Questions about browser_playwright_code

What does the browser_playwright_code tool do? +

Execute arbitrary Playwright code directly. This allows for advanced automation tasks that are not covered by other tools. The code should be wrapped in an async function. Example: (async () => { await page.goto(. It is categorised as a Execute tool in the MCP Macaco Playwright 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_playwright_code? +

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

What risk level is browser_playwright_code? +

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

Can I rate-limit browser_playwright_code? +

Yes. Add a rate_limit block to the browser_playwright_code 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_playwright_code completely? +

Set action: deny in the PolicyLayer policy for browser_playwright_code. 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_playwright_code? +

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