browser_init · Puppeteer Real Browser MCP: Risk & Policy

WHAT IT DOES

What browser_init does on Puppeteer Real Browser

AI agents invoke browser_init to trigger actions in Puppeteer Real Browser. 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_init needs a policy

Launching a browser process is an Execute-class action: it spawns an external process (Chrome) on the host system with anti-detection capabilities, creating a persistent execution environment that can subsequently be used to browse arbitrary sites, exfiltrate data, or carry out further high-impact actions. Anti-detection features increase misuse potential significantly.

From the tool's definition Initialize a new browser instance with anti-detection features and automatic Chrome path detection

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_init Rate-limited

browser_init 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_init": {
      "limits": [
        {
          "counter": "browser_init_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 Puppeteer Real Browser, so you can run agents against it safely.

FAQ

Questions about browser_init

What does the browser_init tool do? +

Initialize a new browser instance with anti-detection features and automatic Chrome path detection. It is categorised as a Execute tool in the Puppeteer Real Browser 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_init? +

Register the Puppeteer Real Browser MCP server in PolicyLayer and add a rule for browser_init: 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 Puppeteer Real Browser. Nothing to install.

What risk level is browser_init? +

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

Can I rate-limit browser_init? +

Yes. Add a rate_limit block to the browser_init 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_init completely? +

Set action: deny in the PolicyLayer policy for browser_init. 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_init? +

browser_init is provided by the Puppeteer Real Browser MCP server (puppeteer-real-browser-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.