browser.launch · MCP Playwright Browser MCP: Risk & Policy

WHAT IT DOES

What browser.launch does on MCP Playwright Browser

AI agents invoke browser.launch to trigger actions in MCP Playwright 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.launch needs a policy

Launching a browser is an Execute-class action: it starts an external process (Chromium) and creates a live browser session. While not destructive or financial on its own, it establishes the environment for subsequent high-risk actions (navigation, scripting, stealth scraping). Misuse could involve spawning many browser processes or initiating automated activity against external sites.

From the tool's definition "Launch Chromium with Playwright and open a new page" — initiates a browser process and creates a new page context, triggering an external operation (browser process execution).

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 Browser, so you can run agents against it safely.

FAQ

Questions about browser.launch

What does the browser.launch tool do? +

Launch Chromium with Playwright and open a new page. It is categorised as a Execute tool in the MCP Playwright 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.launch? +

Register the MCP Playwright Browser 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 Browser. 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 Browser MCP server (mhrnqaruni/mcp-playwright-browser). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.