How to Use the Clientjoy MCP in Vercel AI SDK

Q: How do I stream Clientjoy invoice data using Vercel AI SDK?

You run createMCPClient pointing to your Vinkius MCP URL, then pass listbillinginvoices to streamText. This lets your agent pull the invoice records and render them on your page as the token stream arrives.

Q: Can Vercel AI SDK create new leads in Clientjoy directly?

Yes. Your agent invokes createnewlead when a user enters prospect info in your chat UI. The SDK streams the confirmation status back to your React components instantly.

Q: How do I close the MCP client connection after fetching customer details?

Always call mcpClient.close() inside your API route once getcustomerdetails finishes executing. This prevents open connections from hanging in your serverless environment.

Pipe Clientjoy leads and invoices directly into your React components in real-time with 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 Clientjoy MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live billing updates in your Next.js app

`list_billing_invoices` lets your AI client fetch payment records and render them instantly on the page. Since Vercel AI SDK streams responses, your users watch the invoice list populate row by row instead of staring at a blank loading spinner. You configure `createMCPClient` with the Vinkius endpoint and pass `list_billing_invoices` directly to `streamText`. The SDK handles the connection, letting your React frontend display active Clientjoy billing data the second the model spits it out.

Interactive lead creation via Vercel AI SDK

`create_new_lead` registers fresh business opportunities right from your custom chat interface. Your user describes a prospect, and your agent immediately formats the data and inserts it into your sales pipeline. This setup bypasses slow backend polling by using Edge-compatible routes. You get a fast, responsive form where the agent updates the UI state as soon as the lead hits Clientjoy.

Instant proposal auditing with this MCP Server

`list_sales_proposals` pulls active pitches directly into the Vercel AI SDK context window for instant review. Your agent can compare proposed rates against your actual catalog items retrieved via `list_service_items`. You don't have to build custom API wrappers or manage token refreshes on your own servers. Vinkius keeps the MCP connection alive, letting you stream proposal audits straight to your client-side dashboard.

Setup guide

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

You run `createMCPClient` pointing to your Vinkius MCP URL, then pass `list_billing_invoices` to `streamText`. This lets your agent pull the invoice records and render them on your page as the token stream arrives.

Yes. Your agent invokes `create_new_lead` when a user enters prospect info in your chat UI. The SDK streams the confirmation status back to your React components instantly.

Yes, the setup works perfectly in Edge runtimes. You initialize the client inside your Next.js route handler to fetch proposals or customer lists without hitting serverless cold starts.

Always call `mcpClient.close()` inside your API route once `get_customer_details` finishes executing. This prevents open connections from hanging in your serverless environment.

Your customer records, invoices, and sales proposals never touch persistent external logs. Vinkius runs the server in an isolated, ephemeral sandbox, passing your API credentials directly to Clientjoy over encrypted channels.

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