How to Use the ZenRows MCP in OpenAI Agents SDK

Q: How does ZenRows help with data sources in the OpenAI Agents SDK?

ZenRows provides a stable source of web data. Tools like scrapejs capture JavaScript-rendered HTML, which is crucial for modern websites that hide content until JS runs.

Q: Are there advanced scraping options in ZenRows for the OpenAI Agents SDK?

Absolutely. You have granular control using scrapewait, which lets you wait for a specific CSS selector to appear before capturing the HTML, ensuring nothing gets missed.

Get reliable web content into your OpenAI Agents SDK workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ZenRows MCP to OpenAI Agents SDK

Create your Vinkius account to connect ZenRows 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 ZenRows with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Advanced Web Data Acquisition for OpenAPI Agents

The `scrape_custom` tool lets you build specific scraping logic. You pass in required CSS selectors and wait times, ensuring your agent captures exactly the data it needs from complex pages. Need to deal with heavily protected sites? Use `scrape_antibot`. It provides full anti-bot bypass capabilities, letting your OpenAI Agents SDK gather content that other methods miss.

Visual Data Capture for Your Agent

The `get_screenshot` tool gives you a URL that returns an image of the target page. This is useful when you need to validate visual components or show your agent what it's looking at. It’s a quick way to verify layout integrity before scraping, making sure the data extraction process works visually for your deployed product.

Localized Content Scraping with ZenRows

If your agent needs content specific to a region, `scrape_geo` handles it. You specify countries like 'us' or 'gb', and the MCP Server fetches localized data for you. This keeps your output relevant. It’s better than just getting raw HTML; you get targeted information that directly feeds into your agent's decision-making process.

Setup guide

Set up ZenRows 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 ZenRows tools at runtime.
3

Create your Agent

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

Run the agent

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

ZenRows provides a stable source of web data. Tools like `scrape_js` capture JavaScript-rendered HTML, which is crucial for modern websites that hide content until JS runs.

Yes. The MCP Server connects directly to your agent's execution context. You can use its tools, like `scrape_premium` for higher anonymity scraping, right alongside your existing guardrails.

ZenRows handles everything from raw HTML to clean Markdown. When you pass this content via the MCP Server, your agent receives structured text that validates against its expected inputs.

Absolutely. You have granular control using `scrape_wait`, which lets you wait for a specific CSS selector to appear before capturing the HTML, ensuring nothing gets missed.

ZenRows touches public web content (HTML and structured text). It uses advanced proxy networks to minimize tracking risk while gathering information for your agent's use.

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