Browserbase MCP Server for OpenAI Agents SDK 4 tools — connect in under 2 minutes
The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Browserbase through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
async with MCPServerStreamableHttp(
url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
) as mcp_server:
agent = Agent(
name="Browserbase Assistant",
instructions=(
"You help users interact with Browserbase. "
"You have access to 4 tools."
),
mcp_servers=[mcp_server],
)
result = await Runner.run(
agent, "List all available tools from Browserbase"
)
print(result.final_output)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Browserbase MCP Server
Connect your AI agent to Browserbase — the serverless platform for running headless cloud browsers at scale.
The OpenAI Agents SDK auto-discovers all 4 tools from Browserbase through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Browserbase, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
What you can do
- Create Sessions — Spin up isolated Chromium browser sessions in the cloud. Each session returns a CDP (Chrome DevTools Protocol) WebSocket URL for connecting Playwright, Puppeteer, or Selenium
- List Sessions — Monitor all active, completed, or errored browser sessions across your account
- Get Session Details — Check status, connection URLs, pages visited, and duration of any session
- Stop Sessions — Terminate running sessions to free resources
The Browserbase MCP Server exposes 4 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Browserbase to OpenAI Agents SDK via MCP
Follow these steps to integrate the Browserbase MCP Server with OpenAI Agents SDK.
Install the SDK
Run pip install openai-agents in your Python environment
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com
Run the script
Save the code above and run it: python agent.py
Explore tools
The agent will automatically discover 4 tools from Browserbase
Why Use OpenAI Agents SDK with the Browserbase MCP Server
OpenAI Agents SDK provides unique advantages when paired with Browserbase through the Model Context Protocol.
Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
Browserbase + OpenAI Agents SDK Use Cases
Practical scenarios where OpenAI Agents SDK combined with the Browserbase MCP Server delivers measurable value.
Automated workflows: build agents that query Browserbase, process the data, and trigger follow-up actions autonomously
Multi-agent orchestration: create specialist agents. one queries Browserbase, another analyzes results, a third generates reports
Data enrichment pipelines: stream data through Browserbase tools and transform it with OpenAI models in a single async loop
Customer support bots: agents query Browserbase to resolve tickets, look up records, and update statuses without human intervention
Browserbase MCP Tools for OpenAI Agents SDK (4)
These 4 tools become available when you connect Browserbase to OpenAI Agents SDK via MCP:
create_browser_session
The session provides a connectUrl (CDP WebSocket) that can be used with Playwright, Puppeteer, or Selenium to control the browser programmatically. Default timeout is 300 seconds. Create a new cloud browser session. Returns a CDP WebSocket URL for connecting automation frameworks like Playwright or Puppeteer
get_browser_session
Useful for monitoring active sessions. Get details of a specific browser session by its ID
list_browser_sessions
Filter by status: RUNNING, COMPLETED, ERROR. List all active browser sessions in your Browserbase account
stop_browser_session
Any unsaved state in the browser is lost. Stop a running browser session by its ID
Example Prompts for Browserbase in OpenAI Agents SDK
Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Browserbase immediately.
"Create a new browser session so I can automate a login flow."
"Show me all my running browser sessions."
"Stop browser session sess_abc123."
Troubleshooting Browserbase MCP Server with OpenAI Agents SDK
Common issues when connecting Browserbase to OpenAI Agents SDK through the Vinkius, and how to resolve them.
MCPServerStreamableHttp not found
pip install --upgrade openai-agentsAgent not calling tools
Browserbase + OpenAI Agents SDK FAQ
Common questions about integrating Browserbase MCP Server with OpenAI Agents SDK.
How does the OpenAI Agents SDK connect to MCP?
MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.Can I use multiple MCP servers in one agent?
MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.Does the SDK support streaming responses?
Connect Browserbase with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Browserbase to OpenAI Agents SDK
Get your token, paste the configuration, and start using 4 tools in under 2 minutes. No API key management needed.