browser_launch · MCP Playwright Server MCP: Risk & Policy

WHAT IT DOES

What browser_launch does on MCP Playwright Server

AI agents invoke browser_launch to trigger actions in MCP Playwright 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_launch needs a policy

browser_launch is an Execute category tool because it triggers an external operation (browser process) whose behavior and impact depend on subsequent arguments and commands. While launching a browser itself is not inherently destructive or financial, it enables the agent to perform arbitrary web automation that could include credential theft, unauthorized access, data exfiltration, or injection attacks.

From the tool's definition Tool launches a browser instance with 'optional authentication state and video recording' — initiating an external process that can navigate to arbitrary URLs, execute scripts, and perform actions whose effects depend entirely on how an AI agent directs it.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_launch Rate-limited

browser_launch 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_launch": {
      "limits": [
        {
          "counter": "browser_launch_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 Playwright Server, so you can run agents against it safely.

FAQ

Questions about browser_launch

What does the browser_launch tool do? +

Launch a new browser instance (Chromium, Firefox, or WebKit) with optional authentication state and video recording. It is categorised as a Execute tool in the MCP Playwright 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_launch? +

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

What risk level is browser_launch? +

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

Can I rate-limit browser_launch? +

Yes. Add a rate_limit block to the browser_launch 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_launch completely? +

Set action: deny in the PolicyLayer policy for browser_launch. 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_launch? +

browser_launch is provided by the MCP Playwright Server MCP server (j0hanz/playwright-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.