How to Use the Juhe Data / 聚合数据 MCP in AutoGen

Q: How do I register Juhe Data / 聚合数据 MCP tools with AutoGen agents?

You use mcpservertools with your server URL to fetch the tools. Pass this list directly to your AssistantAgent constructor, and the McpToolAdapter will automatically handle the schema conversion.

Q: Can AutoGen agents negotiate using Juhe Data / 聚合数据 news feeds?

Yes, your agents can use getlatestnews to monitor current events. A trading agent and a risk agent can debate how a specific headline might affect market conditions, using the raw news text as their source of truth.

Q: Do AutoGen agents support the Chinese calendar tools from Juhe Data / 聚合数据?

Yes, your agents can query getcalendarday and getcalendarmonth to coordinate schedules. This allows a planning agent to debate timeline adjustments with a project manager agent based on official Chinese holidays.

Q: How do agents access the driving test questions?

An agent calls getdrivingtestquestions to retrieve a random set of questions. This is useful for building automated training bots where one agent acts as the examiner and the other acts as the student.

Q: How does AutoGen keep sensitive ID and IP lookups private?

All tool calls to getidcardinfo and getiplookup run through our zero-trust, ephemeral MCP server Sandbox. Vinkius never stores or logs the ID numbers or IP addresses processed during agent debates.

Empower your AutoGen agents to debate and verify Chinese market data, local weather, and identity records using this MCP server.

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 AutoGen

Create your Vinkius account to connect Juhe Data / 聚合数据 to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resolve financial debates using AutoGen and live exchange rates

The `get_exchange_rate` tool provides real-time currency pricing to your AutoGen agent conversations. When a financial agent and a budget agent debate transaction costs, they query this tool to settle on a single, verified exchange rate. This consensus-driven approach keeps your automated systems accurate. Because the MCP server delivers raw numbers directly into the chat, agents negotiate using the same live API payload to make final decisions.

Coordinate local logistics using weather and oil prices

The `get_weather` tool delivers current city conditions to your dispatch agents so they can plan routes. A coordinating agent can compare this weather data with regional fuel costs retrieved via `get_oil_price` to calculate shipping surcharges. By debating these variables across multiple specialized agents, your system finds the most cost-effective path. One agent argues for speed based on the weather, while another argues for cost based on fuel prices, settling on an optimal route.

Verify user records through multi-agent consensus

The `get_id_card_info` tool extracts registration details from national IDs to validate user profiles. During onboarding, your security agent can run this check and present the findings to a compliance agent for verification. To strengthen the check, another agent calls `get_ip_lookup` to verify the user's network location. They then debate whether the physical ID registration matches the current IP address before approving the user's account.

Setup guide

Set up Juhe Data / 聚合数据 MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Juhe Data / 聚合数据 tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Juhe Data / 聚合数据_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Juhe Data / 聚合数据 data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Juhe Data / 聚合数据_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Juhe Data / 聚合数据 data")
    print(result.messages[-1].content)

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 AutoGen

You use `mcp_server_tools` with your server URL to fetch the tools. Pass this list directly to your `AssistantAgent` constructor, and the `McpToolAdapter` will automatically handle the schema conversion.

Yes, your agents can use `get_latest_news` to monitor current events. A trading agent and a risk agent can debate how a specific headline might affect market conditions, using the raw news text as their source of truth.

Yes, your agents can query `get_calendar_day` and `get_calendar_month` to coordinate schedules. This allows a planning agent to debate timeline adjustments with a project manager agent based on official Chinese holidays.

An agent calls `get_driving_test_questions` to retrieve a random set of questions. This is useful for building automated training bots where one agent acts as the examiner and the other acts as the student.

All tool calls to `get_id_card_info` and `get_ip_lookup` run through our zero-trust, ephemeral MCP server Sandbox. Vinkius never stores or logs the ID numbers or IP addresses processed during agent debates.

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