How to Use the Yonyou / 用友 MCP in Mastra AI

Q: Does Yonyou / 用友 MCP Server support human review with Mastra AI?

Yes. You can implement a requireToolApproval step in your workflow. This pauses the automated run and requires a human to manually approve the next action based on the retrieved Yonyou data.

Q: What kind of data does this Yonyou / 用友 MCP Server touch?

The server touches core financial data, specifically listvouchers, which requires careful handling in automated workflows.

Build reliable Yonyou backend jobs with Mastra AI.

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 Mastra AI

Create your Vinkius account to connect Yonyou / 用友 to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Handling Purchase Order Failures

To process multiple purchase orders, call `list_purchase_orders` first. Then, build a workflow that conditionally checks the status of each order. If one fails, Mastra AI can automatically retry it with different parameters. This handles complex failure logic, ensuring that if an initial attempt to fetch details (`get_purchase_order`) times out, your job doesn't just stop.

Multi-step Sales Order Fulfillment

Use `list_sales_orders` and combine it with `get_org_info`. You can build a multi-step process: first checking the organization context, then retrieving specific sales order details. If the data is missing, the workflow branches to notify an admin. Mastra AI ensures that these complex operations run reliably from start to finish.

Supplier and Material Verification

When verifying materials or suppliers, combine `list_materials` with `get_inventory`. You can set up a workflow that first checks if the material exists in master data, then verifies its current stock count. This guarantees consistency. The built-in retry mechanism handles temporary network hiccups, keeping your background jobs running even when endpoints are flaky.

Setup guide

Set up Yonyou / 用友 MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Yonyou / 用友 tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "yonyou-mcp-client",
  servers: {
    "yonyou-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Yonyou / 用友 Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Yonyou / 用友 tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Yonyou / 用友 transactions"
);
console.log(result.text);

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 Mastra AI

Mastra AI executes multi-step workflows. For example, it can first list suppliers and then use those IDs to fetch specific details using `get_purchase_order`.

Yes. Its conditional branching allows you to write logic like: 'If the sales order amount is over $10k, then call `get_org_info` for approval before proceeding.'

Yes. You can implement a `requireToolApproval` step in your workflow. This pauses the automated run and requires a human to manually approve the next action based on the retrieved Yonyou data.

The server touches core financial data, specifically `list_vouchers`, which requires careful handling in automated workflows.

It's built for reliability. The automatic retries and exponential backoff ensure that temporary service disruptions won't fail your entire multi-step process.

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