How to Use the Browserless (Playwright Cloud) MCP in OpenAI Agents SDK

Q: How do I configure Browserless (Playwright Cloud) inside OpenAI Agents SDK?

Install the SDK first, then instantiate MCPServerStreamableHttp using your Vinkius endpoint. Pass this MCP server instance directly into your Agent constructor's mcpservers list to let your agents auto-discover the browser tools.

Q: How does caching work with these browser tools?

You should set cacheToolsList=True in your connection parameters. This prevents the SDK from querying the Vinkius MCP endpoint for tool definitions on every single turn, speeding up your agent's response times significantly.

Give your OpenAI Agents SDK production pipelines a headless browser to scrape and screenshot pages without managing infrastructure.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Browserless (Playwright Cloud) MCP to OpenAI Agents SDK

Create your Vinkius account to connect Browserless (Playwright Cloud) 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 Browserless (Playwright Cloud) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Steer clear of bot blocks on OpenAI Agents SDK

Your production agents need clean data, not Cloudflare block screens. This MCP Server gives your deployment the exact tools to bypass anti-bot systems on the fly. By triggering `scrape_with_stealth` or routing requests through `scrape_with_proxy`, your agents pull clean DOM structures without getting flagged. You don't have to write custom browser-evasion logic inside your agent steps anymore. The agent calls these tools natively, securing the raw HTML or screenshots it needs to make its next decision.

Run custom JS inside OpenAI Agents SDK workflows

Some websites won't yield data without a click or a scroll. With `run_custom_function` and `scrape_with_js`, your agent executes raw JavaScript directly inside the remote Playwright instance before pulling down the final state. This allows OpenAI Agents SDK to handle complex single-page apps that rely on heavy client-side rendering. Your agent gets the actual mutated DOM, keeping its context window filled with real data instead of blank loading spinners.

Capture visual proof using this MCP Server

Sometimes text isn't enough to verify a layout or a success state. Your agent can call `get_screenshot` or `get_pdf` to capture exactly what the browser sees, giving you a visual audit trail for every automated run. This visual output plugs straight into your agentic loops. If a page layout changes, the agent catches it visually, logs the error, and hands the task off to a human operator or a recovery agent using OpenAI's built-in tracing.

Setup guide

Set up Browserless (Playwright Cloud) 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 Browserless (Playwright Cloud) tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Browserless (Playwright Cloud) 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="Browserless (Playwright Cloud) Agent",
            instructions="You have access to Browserless (Playwright Cloud) 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 Playwright Cloud. 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 Browserless (Playwright Cloud) 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 Browserless (Playwright Cloud) MCP in OpenAI Agents SDK

Install the SDK first, then instantiate `MCPServerStreamableHttp` using your Vinkius endpoint. Pass this MCP server instance directly into your Agent constructor's `mcp_servers` list to let your agents auto-discover the browser tools.

Yes, you can control tool access at the agent definition level. If you only want an agent to read static text, expose `scrape_elements` and block write-heavy tools like `run_custom_function`.

Yes, you can pass your proxy credentials directly through the `scrape_with_proxy` tool. This lets your OpenAI agents fetch localized content or bypass regional IP restrictions on demand.

You should set `cacheToolsList=True` in your connection parameters. This prevents the SDK from querying the Vinkius MCP endpoint for tool definitions on every single turn, speeding up your agent's response times significantly.

All browser execution happens in ephemeral V8 sandboxes that are wiped clean immediately after your request completes. No raw HTML, PDFs, or screenshots are cached or stored on the Vinkius platform, keeping your sensitive target data completely private.

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