How to Use the Browse AI MCP in OpenAI Agents SDK

Q: How do I connect the Browse AI MCP Server to my OpenAI Agents SDK?

Install the SDK first. Instantiate MCPServerStreamableHttp with your Vinkius endpoint, set cacheToolsList=True, and pass it to the Agent constructor.

Q: Can my OpenAI Agents SDK agent run multiple Browse AI scraping tasks at once?

Yes. Your agent triggers parallel runs using runrobot and monitors them concurrently. The SDK processes these async calls, checking each status via gettask without blocking the main event loop.

Run web scraping robots and fetch clean data inside your OpenAI Agents SDK pipeline without manual API plumbing.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Browse AI MCP to OpenAI Agents SDK

Create your Vinkius account to connect Browse AI 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 Browse AI with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger Web Scraping via OpenAI Agents SDK

Your agent triggers real-time data extraction by executing `run_robot` to spin up a Browse AI task. The OpenAI Agents SDK manages the async execution lifecycle, letting you check progress through `get_task` before passing the extracted data to downstream agents. This MCP setup avoids hardcoded polling loops. If a scraping task stalls, the SDK's built-in tracing catches it, giving you a clear view of the execution state right inside your OpenAI developer dashboard.

Manage Browse AI Monitors and Bulk Runs

Keep tabs on site changes by letting your agent call `create_monitor` to schedule new runs. When you need to scrape at scale, your OpenAI agent pulls the entire history with `list_bulk_runs` and inspects specific batches using `get_bulk_run`. The agent handles the bulk payload directly, feeding the raw structured data into your agentic handoff routines. One specialized agent gathers the run details, validates the schema, and hands it off to a writer agent.

Discover Robots and Check MCP Server Health

Before firing off a massive scraping job, the agent runs `get_system_status` to ensure the Browse AI queue isn't backed up. It uses `list_robots` to find approved scrapers dynamically, avoiding hardcoded robot IDs in your Python codebase. This makes your OpenAI Agents SDK implementation resilient to changes. If a scraper ID changes on the platform, your agent discovers the new one via `get_robot` and adapts its workflow on the fly.

Setup guide

Set up Browse AI 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 Browse AI tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the SDK first. Instantiate `MCPServerStreamableHttp` with your Vinkius endpoint, set `cacheToolsList=True`, and pass it to the `Agent` constructor.

Yes. Your agent triggers parallel runs using `run_robot` and monitors them concurrently. The SDK processes these async calls, checking each status via `get_task` without blocking the main event loop.

If a scraper fails, the SDK captures the failure. You can query `get_system_status` or inspect the task state with `get_task` to handle retries or agent handoffs.

No. The SDK auto-discovers all ten tools from this MCP Server, from `list_monitors` to `run_robot`. You just point the SDK to your Vinkius HTTP endpoint.

Your raw scraped text and extraction payloads remain inside the Vinkius V8 sandbox. The OpenAI Agents SDK only transfers task metadata and extracted JSON over encrypted channels, keeping your target site credentials safe.

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