How to Use the Chargebee MCP in Vercel AI SDK

Q: Tell me how to connect the Chargebee MCP Server to the Vercel AI SDK?

Install the required packages with npm install ai @ai-sdk/mcp. Initialize the connection using createMCPClient with an HTTP transport pointing to your Vinkius endpoint. Then pass those tools into your streamText call.

Q: Can the Vercel AI SDK stream Chargebee invoice data to Next.js?

Yes, the SDK pipes the output of listinvoices directly to your React components as the model processes the tool call. Instead of waiting for a complete JSON response, your users see their billing history appear piece by piece.

Q: In what way does the Vercel AI SDK handle Chargebee subscription creation?

Models invoke createsubscription based on the user's prompt. Implementing the authProvider feature ensures the user actually has permission to modify billing records before the tool executes.

Build live billing dashboards in React by streaming Chargebee data directly to your users 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 Chargebee MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Chargebee MCP Server Data to React

Vercel AI SDK clients pull live billing data without making users stare at a loading spinner. Calling `list_invoices` pipes raw payment records straight into your Next.js frontend as the agent fetches them. Users see their unpaid invoices populate instantly on the screen while the edge function is still running. Building customer portals takes time when you write custom API routes. Now you'll pass `mcpClient.tools()` into `streamText` and let the model handle the heavy lifting. When a user asks about their billing history, the agent runs `get_customer` and streams the formatted response right back to the UI.

Execute Subscriptions from the UI

Interactive chat interfaces fall flat when they only read data. You want them to actually upgrade their plans during a conversation. Hooking up `create_subscription` means the agent can provision a new tier the second the user confirms the price. Edge-compatible tools keep your application fast. Svelte or Vue interfaces update immediately based on the tool execution result, keeping the state perfectly synced with your billing backend. If someone decides to downgrade, the model fires `cancel_subscription` in the background.

Render Dynamic Product Addons

Hardcoding pricing tables is a waste of time when your catalog changes frequently. Running `list_plans` and `list_addons` through the Vercel AI SDK feeds current pricing straight into your chat components. LLMs read the active configurations and format them into a neat comparison table for the user. Vinkius handles the underlying MCP connection so you don't worry about the infrastructure. Developers just run `npm install ai @ai-sdk/mcp` and set up the HTTP transport. After connecting, generative UI components have full read and write access to your revenue operations.

Setup guide

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

Install the required packages with `npm install ai @ai-sdk/mcp`. Initialize the connection using `createMCPClient` with an HTTP transport pointing to your Vinkius endpoint. Then pass those tools into your `streamText` call.

Yes, the SDK pipes the output of `list_invoices` directly to your React components as the model processes the tool call. Instead of waiting for a complete JSON response, your users see their billing history appear piece by piece.

It runs perfectly on the edge. Setup involves initializing the MCP client inside your route handler and fetching tools dynamically. Just remember to call `mcpClient.close()` when the stream finishes.

Models invoke `create_subscription` based on the user's prompt. Implementing the `authProvider` feature ensures the user actually has permission to modify billing records before the tool executes.

Our infrastructure isolates every session in a V8 sandbox. Whenever your app pulls email addresses and payment histories via `get_customer`, that data exists only in ephemeral memory. Sandboxes self-destruct the moment the connection closes.

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