How to Use the Browserbase MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK agent control multiple Browserbase sessions at once?

Yes, the agent can call createbrowsersession multiple times to run parallel browser tasks. Each session gets its own isolated WebSocket URL for independent control.

Spin up cloud browsers directly from your OpenAI Agents SDK workflows without managing local Chromium instances.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Browserbase MCP to OpenAI Agents SDK

Create your Vinkius account to connect Browserbase to OpenAI Agents SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Browserbase with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Spin up cloud browsers from OpenAI Agents SDK

The `create_browser_session` tool provisions a dedicated Chromium instance in the cloud and hands back a raw WebSocket URL. Your agent uses this URL to connect Playwright or Puppeteer directly, bypassing the pain of local browser installation. This setup lets your agent run complex web automation tasks. Running this MCP Server gives you cloud browser instances on demand without cluttering your execution environment.

Monitor running sessions in real time

The `get_browser_session` tool retrieves the exact status and metadata of any active browser instance. If an agent gets stuck on a login screen, you can inspect the session state immediately. Tracking these instances ensures your agent systems don't leave orphaned browsers running in the background. You get full visibility into what your automated workflows are doing at any second.

Bulk session management and clean termination

The `list_browser_sessions` tool audits your active cloud browsers, while `stop_browser_session` kills specific instances instantly. Clean up stale environments programmatically before they eat up your active session limits. Managing resources this way keeps your agent runs fast and cheap. This MCP setup prevents runaway loops from keeping headless browsers alive indefinitely.

Setup guide

Set up Browserbase MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Browserbase tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Browserbase tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Browserbase tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Browserbase Agent",
            instructions="You have access to Browserbase tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Browserbase. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Browserbase now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Browserbase MCP in OpenAI Agents SDK

Install the package using pip, then initialize the server streamable HTTP class with your Vinkius endpoint. Pass this server object into your agent constructor to let your model discover the tools automatically.

Yes, the agent can call `create_browser_session` multiple times to run parallel browser tasks. Each session gets its own isolated WebSocket URL for independent control.

The default timeout is 300 seconds per session. Your python code can monitor this limit and use `stop_browser_session` to shut down the connection early if the task finishes.

No, the server gives your agent the CDP WebSocket URL directly. You just feed that URL into your existing Playwright or Puppeteer connection code.

All WebSocket traffic and active browser session data run inside ephemeral, zero-trust sandboxes. Vinkius secures the connection token, and Browserbase destroys the container once you call `stop_browser_session`, leaving no cached credentials behind.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript