How to Use the Kingdee / 金蝶 MCP in LangChain

Build reliable Kingdee ERP workflows using LangChain. Chain data queries into automated form approvals with full tracing.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kingdee / 金蝶 MCP to LangChain

Create your Vinkius account to connect Kingdee / 金蝶 to LangChain 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 Kingdee / 金蝶 with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Agentic ERP workflows

Connect your LangChain agents straight to the ERP. They read business context and execute multi-step procurement sequences without human intervention. You map out the logic. The agent pulls inventory via `query_data`, drafts a new purchase order using `save_form`, and pushes it through `submit_form`. You get consistent execution every time.

Approval pipelines with this MCP Server

Approval chains get complicated fast. This MCP Server gives your ReAct agents the exact hooks needed to manage state transitions across your entire organization. When an agent spots an anomaly, it triggers `un_audit_form` to pull a record back. Routine approvals hit `audit_form` instantly. You handle the logic while the adapter manages the API translation.

Deep organizational context

Agents need hierarchy data to route requests correctly. LangChain pulls this context dynamically before making any routing decisions. The agent grabs department structures via `get_org_info`. It cross-references active records using `list_forms` and `view_form`. Everything shows up in LangSmith so you know exactly why an agent routed a form to a specific manager.

Setup guide

Set up Kingdee / 金蝶 MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Kingdee / 金蝶 tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "kingdee-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Kingdee / 金蝶 transactions"
    })
    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 Kingdee / 金蝶. 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 Kingdee / 金蝶 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 Kingdee / 金蝶 MCP in LangChain

Use the langchain-mcp-adapters package. Initialize MultiServerMCPClient with the endpoint URL. Call client.get_tools() and pass them directly into your agent constructor.

Yes. You provide the rules for when an agent should use the audit_form tool. If the conditions fail, the agent can reject the request or trigger status_convert to flag it.

All tool invocations pipe straight into LangSmith. You see exactly what payload went into save_form and how long the ERP took to respond. This makes debugging hallucinated form data trivial.

You chain the tools. The agent checks current states using view_form. Then it executes status_convert to move materials through the required business stages.

Vinkius runs the integration inside a V8 Isolate sandbox. Your material records, organizational hierarchies, and financial forms never leak into persistent storage. The session dies the moment the chain finishes executing.

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