How to Use the Cloopen / 容联云 MCP in Vercel AI SDK

Q: How do I connect the Cloopen / 容联云 MCP Server to my Vercel AI SDK project?

Install @ai-sdk/mcp and set up the HTTP transport with your Vinkius endpoint. Pass the server tools directly into generateText or streamText to let your agent trigger SMS and voice campaigns.

Q: Can I run Cloopen / 容联云 voice callbacks inside Vercel Edge Functions?

Yes. The listcallback tool works perfectly inside Edge environments because the Vinkius MCP Server handles the heavy API handshake. Your Vercel AI SDK client just sends the two target phone numbers and handles the immediate JSON response.

Q: How does the Vercel AI SDK handle Cloopen / 容联云 SMS template errors?

When sendsms fails due to an invalid template ID, the server returns the raw error code. Your agent reads this error from the tool output and can automatically suggest alternative templates by calling listtemplates.

Q: Do I need to manage connection pools for Cloopen / 容联云 queries in Vercel AI SDK?

No. Always call mcpClient.close() at the end of your Vercel AI SDK execution block to clean up the SSE or HTTP connections. This prevents socket leaks in serverless environments.

Trigger live Cloopen / 容联云 voice calls and track SMS delivery directly inside your Vercel AI SDK interface.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cloopen / 容联云 MCP to Vercel AI SDK

Create your Vinkius account to connect Cloopen / 容联云 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 Cloopen / 容联云 with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live-Streaming SMS Status Updates

The `query_sms` tool pulls real-time delivery logs directly from China's cellular networks into your Vercel AI SDK stream. Instead of forcing users to stare at a blank screen while waiting for network confirmation, the agent streams the exact delivery status of each message to the frontend as it updates. You hook this tool into `streamText` and let your React components render the state changes instantly. This cuts down on API polling because the live connection feeds the UI directly, giving your users immediate visual feedback on their SMS campaigns.

Interactive Voice Verifications via MCP Server

The `list_voice_codes` tool triggers automated voice verification calls to Chinese phone numbers and returns the dispatch status to your application. When a user requests a login code, your Vercel AI SDK client calls this tool to fire off the voice call immediately. By deploying this on Vercel Edge Functions, you keep latency low. The tool bypasses heavy backend wrappers, allowing your frontend to display call confirmation states in real-time while the user's phone is actually ringing.

Real-Time Account and IVR Auditing

The `get_account_info` and `get_ivr` tools fetch your current Cloopen API balances and interactive voice response configurations. Your AI client reads these metrics to warn you if funds are too low to run your current voice campaign. Using these tools within your Next.js dashboard lets you build self-monitoring admin panels. Your agent checks the account limits, flags any misconfigured IVR routes, and displays the corrective actions directly in the chat interface.

Setup guide

Set up Cloopen / 容联云 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 Cloopen / 容联云 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 Cloopen / 容联云 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 Cloopen / 容联云. 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 Cloopen / 容联云 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 Cloopen / 容联云 MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and set up the HTTP transport with your Vinkius endpoint. Pass the server tools directly into `generateText` or `streamText` to let your agent trigger SMS and voice campaigns.

Yes. The `list_callback` tool works perfectly inside Edge environments because the Vinkius MCP Server handles the heavy API handshake. Your Vercel AI SDK client just sends the two target phone numbers and handles the immediate JSON response.

When `send_sms` fails due to an invalid template ID, the server returns the raw error code. Your agent reads this error from the tool output and can automatically suggest alternative templates by calling `list_templates`.

No. Always call `mcpClient.close()` at the end of your Vercel AI SDK execution block to clean up the SSE or HTTP connections. This prevents socket leaks in serverless environments.

Vinkius processes all data through isolated V8 sandboxes, meaning phone numbers and SMS payloads never persist on disk. Your API keys are injected at the proxy layer, so your frontend code never exposes your Cloopen credentials to the client.

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