How to Use the Diffbot MCP in OpenAI Agents SDK

Q: How do I configure Diffbot within my OpenAI Agents SDK project?

You initialize the server via MCPServerStreamableHttp and pass it to your agent constructor. It handles discovery of all 10 extraction tools automatically.

Q: Can I use Diffbot to extract product data for an OpenAI Agents SDK agent?

Yes. Call extractproduct with your target URL. The tool returns the price, description, and metadata as clean JSON ready for your agent.

Q: Does Diffbot work with the OpenAI Agents SDK for article extraction?

Absolutely. Use extractarticle to pull text from news sites. It filters out comments and ads so your agent processes only the core content.

Turn messy web pages into clean JSON for your OpenAI Agents SDK projects with Diffbot.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Diffbot MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Auto-classify pages with your OpenAI Agents SDK

Stop writing brittle regex for every site. Use `analyze_page` to let the server decide if you're looking at a product, job, or article and return structured data automatically. This setup works perfectly within your Python agent pipeline. Your agent gets clean JSON without you needing to define schemas for every new domain.

Production-grade extraction for OpenAI Agents SDK

Feed complex e-commerce or news sites into `extract_product` or `extract_article`. These tools handle the heavy lifting of DOM traversal so your agent doesn't get stuck on pagination or layout shifts. It's built for production reliability. You define the URL, the MCP server does the rest, and your agent acts on the validated output immediately.

Specialized scraping for OpenAI Agents SDK

Target specific data types like forum discussions or event schedules using `extract_discussion` and `extract_event`. These tools isolate the relevant content and discard the surrounding noise. Your agent remains focused on the data that matters. Since the response is structured, your guardrails can validate the information before the agent takes any further action.

Setup guide

Set up Diffbot 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 Diffbot tools at runtime.
3

Create your Agent

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

Run the agent

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

You initialize the server via `MCPServerStreamableHttp` and pass it to your agent constructor. It handles discovery of all 10 extraction tools automatically.

Yes. Call `extract_product` with your target URL. The tool returns the price, description, and metadata as clean JSON ready for your agent.

Absolutely. Use `extract_article` to pull text from news sites. It filters out comments and ads so your agent processes only the core content.

The server returns status codes directly from the API. Your Python agent should catch these exceptions to manage retries or log failures.

Diffbot processes the requested URL and returns the extracted JSON to your agent. No PII is stored on our side; we only handle the web page content.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.