How to Use the Juhe Data / 聚合数据 MCP in OpenAI Agents SDK

Q: What are some use cases for Juhe Data / 聚合数据 and the OpenAI Agents SDK?

You could build a financial agent that uses getexchangerate and getoilprice for market analysis. Or, create a logistics agent that uses getweather and getiplookup for planning routes in China. The SDK's tracing helps you monitor these production workflows.

Build production agents with the OpenAI SDK and give them instant access to Chinese market data from Juhe Data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Juhe Data / 聚合数据 MCP to OpenAI Agents SDK

Create your Vinkius account to connect Juhe Data / 聚合数据 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 Juhe Data / 聚合数据 with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Real-Time Chinese Financial Data

This toolset plugs your agent directly into China's market data. You can have your agent track currency fluctuations with `get_exchange_rate` or monitor domestic fuel costs using `get_oil_price`. It's not just about getting the data; it's about letting the agent act on it within the safety of the OpenAI framework. Because the tools are exposed through a Vinkius MCP server, your agent discovers them automatically. You don't write boilerplate API code. You just tell your agent its goal, and it figures out how to use the tools to get there. One agent could monitor oil prices and another could execute trades based on currency rates, all coordinated by the SDK.

Verify Identity and Location with Guardrails

The server includes tools for sensitive operations, like `get_id_card_info` for identity checks and `get_ip_lookup` for geolocating users. These are essential for any service operating in China. The OpenAI Agents SDK is built for this kind of work, providing guardrails and handoffs between specialized agents. You can build one agent that handles the PII request and another that processes the result, all with full tracing in your OpenAI dashboard. This separation of concerns is critical for compliance. You know exactly which agent accessed sensitive data and when, giving you an audit trail out of the box.

Add Utility Tools to your OpenAI MCP Server

Round out your agent's abilities with a set of practical, everyday tools. It can check local conditions with `get_weather`, pull holiday schedules with `get_calendar_day`, or even grab the latest headlines from `get_latest_news`. These aren't groundbreaking on their own, but they make your agent much more useful. These simple tools are perfect for building agents that handle customer support or internal automation. An agent can check if it's a holiday before scheduling a task or pull a local weather forecast before dispatching a delivery. This MCP server gives your agent the context it needs to make smarter decisions.

Setup guide

Set up Juhe Data / 聚合数据 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 Juhe Data / 聚合数据 tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Juhe Data / 聚合数据 tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Juhe Data / 聚合数据 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="Juhe Data / 聚合数据 Agent",
            instructions="You have access to Juhe Data / 聚合数据 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 Juhe Data / 聚合数据. 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 Juhe Data / 聚合数据 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 Juhe Data / 聚合数据 MCP in OpenAI Agents SDK

You instantiate the MCP server with your Vinkius endpoint and pass it to your Agent constructor. The OpenAI agent automatically discovers all the Juhe Data tools—like `get_weather` and `get_exchange_rate`—and knows how to call them.

Yes. While the agent discovers all tools by default, you can implement logic on your side to restrict which tools a specific agent is allowed to invoke. This is a standard pattern for building specialized agents with limited scopes.

You could build a financial agent that uses `get_exchange_rate` and `get_oil_price` for market analysis. Or, create a logistics agent that uses `get_weather` and `get_ip_lookup` for planning routes in China. The SDK's tracing helps you monitor these production workflows.

The Vinkius platform is designed for low latency. For best performance with the OpenAI SDK, set `cacheToolsList=True` in your agent's configuration. This prevents the agent from re-fetching the tool list on every run.

The Vinkius MCP server that processes the request is completely ephemeral. It spins up in a zero-trust sandbox, handles the call to Juhe Data for the Chinese ID card info, passes the response to your agent, and is then destroyed. No data is ever stored on the server.

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