How to Use the Olostep MCP in OpenAI Agents SDK

Q: How do I install the Olostep MCP Server for my OpenAI Agents SDK project?

Run pip install openai-agents to start. Then, configure your agent with MCPServerStreamableHttp pointing to your Vinkius endpoint, passing it into the mcpservers list.

Q: Can my OpenAI Agents SDK agent run parallel scrapes with Olostep?

Yes. The agent uses createbatch to submit a list of target URLs, then polls getbatchresults to retrieve the structured markdown once the jobs complete.

Q: Can I optimize tool loading times during startup?

Yes, set cacheToolsList=True in your connection parameters. This prevents the SDK from querying the MCP server for its tool list on every single agent interaction.

Run headless browser scrapes directly inside your OpenAI Agents SDK workflows using this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Olostep MCP to OpenAI Agents SDK

Create your Vinkius account to connect Olostep to OpenAI Agents SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Olostep with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Parallel bulk scraping with OpenAI Agents SDK

You need to scrape a list of URLs and feed them to your OpenAI Agents SDK agent. Instead of making synchronous requests that block your execution loop, your agent can call `create_batch` to fire off a bulk scraping job. The agent then monitors the job status using `get_batch` and pulls down the clean markdown or HTML via `get_batch_results` once it is done. This keeps your agent's decision loops fast and prevents timeouts on long-running network operations.

Dynamic JS rendering on demand

Heavy JavaScript sites often break basic scrapers, but your agent can handle them easily by invoking `scrape_url`. This tool instructs Olostep to spin up a headless browser, execute the JS, and return clean structured text directly to the OpenAI Agents SDK context. Before running a heavy scrape, the agent can run `check_olostep_status` to ensure the scraper API is fully responsive. This prevents wasteful LLM calls to broken endpoints and keeps your agent's execution path clean.

Self-monitoring API credits and agents

OpenAI Agents SDK runs can get expensive if an agent loops out of control, so you need guardrails. The agent can query `get_usage` before spinning up a massive scrape task to verify you still have budget left. If you use custom scraping agents, the agent can use `list_agents` and `get_agent` to pick the right scraping profile dynamically. This keeps your data collection modular and lets the agent swap scraping configurations on the fly.

Setup guide

Set up Olostep 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 Olostep tools at runtime.
3

Create your Agent

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

Run the agent

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

Run `pip install openai-agents` to start. Then, configure your agent with `MCPServerStreamableHttp` pointing to your Vinkius endpoint, passing it into the `mcp_servers` list.

Yes. The agent uses `create_batch` to submit a list of target URLs, then polls `get_batch_results` to retrieve the structured markdown once the jobs complete.

It happens automatically. When you register the MCP server in the agent constructor, the SDK auto-discovers tools like `scrape_url` and `get_usage` with zero manual configuration.

Yes, set `cacheToolsList=True` in your connection parameters. This prevents the SDK from querying the MCP server for its tool list on every single agent interaction.

All scraped HTML content and target URLs are processed within isolated Vinkius sandboxes. Your raw data is never cached permanently or used to train models, keeping your target URLs and extracted page data strictly confidential.

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