How to Use the Chuanyun MCP in Vercel AI SDK

Q: How do I connect Chuanyun to Vercel AI SDK?

Pass the endpoint URL to createMCPClient({ transport: { type: "http", url: "..." } }). Then call mcpClient.tools() and feed the output into streamText. Always run mcpClient.close() when the request finishes.

Q: Can Vercel AI SDK create Chuanyun business objects?

Yes, the createbizobject tool handles that. Your agent maps the user's chat input to the required form schema and pushes the new record to the backend.

Q: How do I read Chuanyun workflow history in Vercel AI SDK?

You expose the getworkflowhistory tool to your generateText call. The agent reads the approval timeline and formats it for your React frontend.

Stream Chuanyun enterprise workflow data directly into React frontends using 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 Chuanyun MCP to Vercel AI SDK

Create your Vinkius account to connect Chuanyun 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 Chuanyun with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Form Schemas to the UI

The `get_form_schema` and `list_forms` tools let Vercel AI SDK pull exact field requirements from Chuanyun. Your Next.js application queries the MCP Server and streams the required inputs straight to the user's browser. End users see dynamic forms build themselves in real-time. Instead of hardcoding ERP layouts, your React components render the exact fields the server demands.

Live Business Object Updates

Using `update_biz_object` and `list_biz_objects`, your agent modifies enterprise records while pushing UI state changes instantly. The edge function executes the change via the MCP protocol and streams the confirmation back. Users watch their dashboard update the second a record changes. You avoid loading spinners completely because the SDK handles the HTTP transport layer in the background.

Display Workflow Histories

The `get_workflow_history` tool pulls approval chains and step-by-step audit trails from the Chuanyun backend. Your Vercel AI SDK implementation pipes this raw array data directly into a timeline component. Managers can review who approved what without leaving your custom interface. The agent fetches the exact instance history and renders it before the user even finishes asking for the status.

Setup guide

Set up Chuanyun 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 Chuanyun 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 Chuanyun 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 Chuanyun. 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 Chuanyun 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 Chuanyun MCP in Vercel AI SDK

Pass the endpoint URL to `createMCPClient({ transport: { type: "http", url: "..." } })`. Then call `mcpClient.tools()` and feed the output into `streamText`. Always run `mcpClient.close()` when the request finishes.

Yes, the `create_biz_object` tool handles that. Your agent maps the user's chat input to the required form schema and pushes the new record to the backend.

It works perfectly in edge environments. The Vercel AI SDK handles the HTTP transport to the Vinkius URL without relying on Node-specific dependencies.

You expose the `get_workflow_history` tool to your `generateText` call. The agent reads the approval timeline and formats it for your React frontend.

Your business objects, approval histories, and user lists stay protected inside the Vinkius V8 isolate sandbox. The server spins up an ephemeral instance just for your session and destroys itself after the edge function terminates.

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