How to Use the Yonyou / 用友 MCP in AutoGen

Q: How does AutoGen use Yonyou / 用友 data for decision-making?

Agents discuss tool outputs. If one agent calls listpurchaseorders and finds an issue, a second agent can call getorginfo to determine if the organizational unit is authorized to proceed.

Q: What happens when I run Yonyou / 用友 financial analysis with AutoGen?

The agents debate the findings. One agent calls listvouchers to pull transaction lists, and a second agent might use getpurchaseorder data to verify which department caused the expense.

Q: Is Yonyou / 用友 customer listing reliable when used with AutoGen?

The agents treat the output of listcustomers as a variable fact. They will use it in conversation, challenging assumptions and verifying data points against other tools.

Resolve Complex ERP Decisions with AutoGen using Yonyou / 用友 Data

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Yonyou / 用友 MCP to AutoGen

Create your Vinkius account to connect Yonyou / 用友 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 Yonyou / 用友 with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Simulate purchase order approval debates

Setup multiple agents to discuss a potential issue. One agent pulls current data via `get_purchase_order`. A second agent, acting as an auditor, then challenges that data by calling `list_vouchers` to ensure compliance. The negotiation process forces convergence on a decision, identifying risks the initial query might have missed.

Validate sales processes through debate

Have agents argue over whether an order is complete. One agent checks `get_sales_order` details, while another calls `list_customers` to verify account status. They must reach consensus on the next steps. This conversational framework handles scenarios where the answer isn't obvious and requires multiple perspectives.

Determine material availability via argument

You can run a simulation where agents debate material usage. One agent uses `list_materials` for definitions, while another checks real-time stock using `get_inventory`. They negotiate whether the requested material is actually available. The system converges on an actionable status based on conflicting data inputs.

Setup guide

Set up Yonyou / 用友 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 Yonyou / 用友 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="Yonyou / 用友_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Yonyou / 用友 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="Yonyou / 用友_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Yonyou / 用友 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 Yonyou / 用友. 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 Yonyou / 用友 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 Yonyou / 用友 MCP in AutoGen

Agents discuss tool outputs. If one agent calls `list_purchase_orders` and finds an issue, a second agent can call `get_org_info` to determine if the organizational unit is authorized to proceed.

Yes. You set up agents to debate stock levels. One agent queries `get_inventory`, and another might challenge it by listing associated materials via `list_materials`.

The agents debate the findings. One agent calls `list_vouchers` to pull transaction lists, and a second agent might use `get_purchase_order` data to verify which department caused the expense.

The agents treat the output of `list_customers` as a variable fact. They will use it in conversation, challenging assumptions and verifying data points against other tools.

The server handles supplier information details. This data is critical for agents debating procurement options or validating source material during multi-agent conversations.

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