launch_browser · MCP Playwright Server MCP: Risk & Policy

WHAT IT DOES

What launch_browser does on MCP Playwright Server

AI agents invoke launch_browser 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 launch_browser needs a policy

This tool triggers execution of an external process (browser launch) whose effects depend on arguments and subsequent tool calls. While launching a browser itself is not destructive or financial, it is an Execute action because it initiates an external operation that could be chained with other tools (navigate, click, type_text) to perform arbitrary browser-based actions.

From the tool's definition Tool 'launch_browser' launches a new browser instance, which is an external operation that initiates a new process.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

launch_browser Rate-limited

launch_browser 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": {
    "launch_browser": {
      "limits": [
        {
          "counter": "launch_browser_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 launch_browser

What does the launch_browser tool do? +

Launch a new browser instance. 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 launch_browser? +

Register the MCP Playwright Server MCP server in PolicyLayer and add a rule for launch_browser: 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 launch_browser? +

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

Can I rate-limit launch_browser? +

Yes. Add a rate_limit block to the launch_browser 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 launch_browser completely? +

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

launch_browser is provided by the MCP Playwright Server MCP server (mostafaraafat91/mcp-playwright-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.