launch-browser · Mcp Playwright Test MCP: Risk & Policy

WHAT IT DOES

What launch-browser does on Mcp Playwright Test

AI agents invoke launch-browser to trigger actions in Mcp Playwright Test. 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

Browser launching is an external operation that triggers a system process whose effects (what the browser does) depend on how it is subsequently controlled. This falls under Execute rather than Read or Write because it initiates an external tool/process. Severity is high because a compromised browser instance could be used for credential theft, malware injection, or unauthorized API calls.

From the tool's definition Tool name 'launch-browser' and server context indicate it launches a browser instance. The sibling tools (execute-api-tests, execute-ui-tests) and server description (automates Playwright-based UI testing) confirm this tool performs external operations.

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 Test, so you can run agents against it safely.

FAQ

Questions about launch-browser

What does the launch-browser tool do? +

launch-browser. It is categorised as a Execute tool in the Mcp Playwright Test 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 Test 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 Test. 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 Test MCP server (w1561778301/mcp-playwright-test). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.