How to Use the Kingdee / 金蝶 MCP in Vercel AI SDK

Q: How do I connect Kingdee / 金蝶 to Vercel AI SDK?

Use createMCPClient from @ai-sdk/mcp and point it to your Vinkius endpoint. Pass the tools directly to streamText to let your LLM query and update records.

Q: Can I stream Kingdee / 金蝶 ledger data to a React frontend using Vercel AI SDK?

Yes. The querydata tool retrieves the raw data, and the SDK streams the parsed results directly into your UI components without intermediate API endpoints.

Build real-time Next.js ERP portals where Kingdee / 金蝶 data streams directly into the UI using the Vercel AI SDK.

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 Vercel AI SDK

Create your Vinkius account to connect Kingdee / 金蝶 to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Direct ERP queries via Vercel AI SDK

The `query_data` tool lets your React or Next.js frontend pull raw financial records directly from the ERP without writing custom API routes. Your AI client calls this tool, and the raw ledger details stream straight to the client's screen. This setup cuts out the typical loading spinner delay because the MCP Server pushes the stream of data block by block. You don't have to wait for a heavy server-side payload to resolve before rendering the table.

Instant material form submission

The `save_form` and `submit_form` tools let users draft and queue procurement requests inside a live chat window. The AI client handles the payload formatting on the fly, matching the exact schema required by Kingdee. Because this MCP integration runs directly inside Vercel's Edge runtime, you get fast execution speeds. Your users can review the drafted form, make edits in real-time, and submit it instantly without leaving the page.

One-click status changes and audits

The `status_convert` and `audit_form` tools allow managers to approve or revoke financial documents directly from a streaming interface. The AI client handles the state transitions in the background, updating the UI as soon as the ERP registers the change. If a manager spots an error, they can trigger `un_audit_form` to roll back the status. The entire flow runs over a secure MCP connection, keeping your backend credentials hidden from the client browser.

Setup guide

Set up Kingdee / 金蝶 MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Kingdee / 金蝶 tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Kingdee / 金蝶 transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Use `createMCPClient` from `@ai-sdk/mcp` and point it to your Vinkius endpoint. Pass the tools directly to `streamText` to let your LLM query and update records.

Yes. The `query_data` tool retrieves the raw data, and the SDK streams the parsed results directly into your UI components without intermediate API endpoints.

Vinkius manages the ERP credentials securely. Your Next.js app uses a single Vinkius token in the `createMCPClient` transport configuration to authenticate all requests.

The SDK catches the API error and exposes it to your frontend error boundary. You can handle the failure state gracefully without crashing the active user session.

This MCP Server runs in a sandboxed V8 isolate on Vinkius, meaning your raw database credentials and API tokens never touch the client's browser or the Vercel edge network directly.

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