How to Use the Mingdao Cloud MCP in Vercel AI SDK

Q: How do I stream Mingdao Cloud worksheet data using Vercel AI SDK?

You call listrows through the MCP connection and pass the tools array to streamText. This lets your frontend render row data chunk-by-chunk as it arrives from your worksheet.

Q: Can I write new records to Mingdao Cloud from Vercel AI SDK?

Yes, you use the addrow tool within your tool-calling block. The SDK triggers the operation and streams the success status back to your UI immediately.

Q: How does this Mingdao Cloud MCP Server handle database schema changes in Vercel AI SDK?

Your agent calls getworksheetschema to inspect the live field definitions. The Vercel AI SDK uses this schema to render matching input fields dynamically in your React forms.

Q: Do I need to manage connection pooling for this setup?

No, but you must call mcpClient.close() when your edge function completes its stream. This prevents leaking connections to the Mingdao Cloud API endpoints.

Build web apps that stream live Mingdao Cloud worksheet data directly into React components 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 Mingdao Cloud MCP to Vercel AI SDK

Create your Vinkius account to connect Mingdao Cloud 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 Mingdao Cloud with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream worksheet schemas to Vercel AI SDK frontends

The `get_worksheet_schema` tool lets your agent inspect the structure of your Mingdao Cloud tables before rendering them. Instead of waiting for a full page reload, the client streams the field types directly into your React UI components. You use `list_worksheets` to fetch the available tables, and the Vercel AI SDK pipes this structural data into your frontend state. This setup eliminates loading spinners because the interface updates as soon as the schema bytes hit the edge.

Edit Mingdao Cloud rows dynamically in the UI

The `add_row` tool lets your Next.js application insert new records into Mingdao Cloud worksheets instantly. This works by piping commands through the MCP Server directly to your database. If a user edits a cell, the agent calls `update_row` to modify the record. You close the connection with `mcpClient.close()` once the streaming session completes to keep edge execution times low.

Run Mingdao Cloud workflows via the MCP Server

The `list_workflows` tool exposes active automation pipelines to your Vercel AI SDK application. Your agent queries this endpoint to show users which automated processes are running alongside their data. By combining `get_app_info` with this list, your interface displays a live dashboard of your enterprise platform. This gives users immediate visibility into background actions without leaving your custom frontend.

Setup guide

Set up Mingdao Cloud 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 Mingdao Cloud 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 Mingdao Cloud 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 Mingdao Cloud. 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 Mingdao Cloud 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 Mingdao Cloud MCP in Vercel AI SDK

You call `list_rows` through the MCP connection and pass the tools array to `streamText`. This lets your frontend render row data chunk-by-chunk as it arrives from your worksheet.

Yes, you use the `add_row` tool within your tool-calling block. The SDK triggers the operation and streams the success status back to your UI immediately.

Your agent calls `get_worksheet_schema` to inspect the live field definitions. The Vercel AI SDK uses this schema to render matching input fields dynamically in your React forms.

No, but you must call `mcpClient.close()` when your edge function completes its stream. This prevents leaking connections to the Mingdao Cloud API endpoints.

The MCP Server processes your Mingdao Cloud worksheet records, user profiles, and workflow metadata. Vinkius isolates this traffic in an ephemeral sandbox, passing your data directly to the API without storing it.

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