AI agents invoke create_browser_session to trigger actions in Mcp Playwright. 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.
Creating a browser session initiates an external browser process, which is an Execute-category action. It triggers an external operation (browser instantiation) whose effects depend on the execution environment. While not destructive on its own, it enables subsequent browser automation actions and has medium severity as it opens an attack surface for web-based operations.
From the tool's definition 创建新的浏览器会话 (Create new browser session) — launches an external browser process/session
Documented attack patterns abuse exactly the kind of access create_browser_session gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Playwright, and nothing reaches the server without passing your rules. This is the rule we recommend for create_browser_session:
{
"version": "1",
"default": "deny",
"tools": {
"create_browser_session": {
"limits": [
{
"counter": "create_browser_session_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}create_browser_session 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.
Free to start. No card required.
创建新的浏览器会话. It is categorised as a Execute tool in the Mcp Playwright MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Playwright MCP server in PolicyLayer and add a rule for create_browser_session: 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. Nothing to install.
create_browser_session is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the create_browser_session 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.
Set action: deny in the PolicyLayer policy for create_browser_session. 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.
create_browser_session is provided by the Mcp Playwright MCP server (ma-pony/mcp-playwright). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Playwright, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
12 Mcp Playwright tools catalogued and risk-classified — across an index of 43,000+ MCP servers.