How to Use the Yonyou / 用友 MCP in CrewAI

Automate Yonyou operations using a specialized team with CrewAI.

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 CrewAI

Create your Vinkius account to connect Yonyou / 用友 to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous Procurement Analysis

Assign one agent to research the available suppliers by calling `list_suppliers`. A second agent analyzes this list against required materials using `list_materials`. The final moderator agent then generates a summary report of potential sourcing options. This role-based specialization means you don't just get data; you get an actionable conclusion about which vendors fit your needs.

Financial Audit Workflow

Set up agents where Agent A retrieves all financial vouchers using `list_vouchers`. Agent B then analyzes these records to spot discrepancies against current sales order data (`list_sales_orders`). The third agent formats the final audit report. It's a true assembly line of intelligence, running autonomous operations without needing human intervention at every step.

Inventory and Organization Context

Use an initial agent to get core organizational metadata via `get_org_info`. A second agent then uses this context to query specific inventory details using `get_inventory` against the correct warehouse location. This ensures accuracy. The shared memory allows agents to pass context—like a department ID or branch code—from one step to the next, making complex operations possible.

Setup guide

Set up Yonyou / 用友 MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Yonyou / 用友 tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Yonyou / 用友 Analyst",
    goal="Access and analyze Yonyou / 用友 data via MCP.",
    backstory="Expert analyst with direct Yonyou / 用友 access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Yonyou / 用友 transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Yonyou / 用友 Analyst",
        goal="Access and analyze Yonyou / 用友 data via MCP.",
        backstory="Expert analyst with direct Yonyou / 用友 access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Yonyou / 用友 transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

CrewAI treats your tools as specialized knowledge. You pass the `yonyou-mcp` endpoint, and its agents use tools like `list_purchase_orders` to gather facts needed for their collaborative tasks.

Absolutely. You can build autonomous pipelines—for example, a team that researches suppliers and automatically drafts a preliminary purchase order draft based on current stock levels.

This server touches all major operational areas: sales orders (`list_sales_orders`), purchasing details, and financial records like vouchers. The team can tackle any combination.

You pass the URL directly in your agent configuration. For advanced setups, you use `tool_filter` to expose only the necessary tools—like just inventory checks—to prevent confusion.

The server accesses customer and supplier master data, as well as detailed financial voucher records (`list_vouchers`), which requires careful permission handling.

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