How to Use the Dola Checkout MCP in Vercel AI SDK

Q: How do I stream a live payment link using Dola Checkout and Vercel AI SDK?

Use createcheckout inside your streamText tool definition. The Vercel AI SDK calls the Dola Checkout MCP server, gets the session URL, and streams it straight to your React component.

Q: Can I update order statuses dynamically with Dola Checkout in Vercel AI SDK?

Yes, by passing updateorder to your model's tools array. The agent listens to the user's request, executes the status change, and streams the updated order object back to the UI.

Q: How do I close the MCP connection when the stream ends?

Always call mcpClient.close() once your text generation or streaming loop finishes. This prevents memory leaks in your Edge Functions and keeps your serverless execution times low.

Stream real-time payment interfaces and instant checkout states directly into your React app 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 Dola Checkout MCP to Vercel AI SDK

Create your Vinkius account to connect Dola Checkout 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 Dola Checkout with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live-Streaming Payment Sessions

The `create_checkout` and `get_checkout` tools let your frontend generate payment sessions on the fly. When a user tells your agent they want to buy, the SDK streams the active checkout session straight into the DOM. You skip the typical API-to-state-management boilerplate completely. Edge compatibility means these calls run close to your users. Your Vercel AI SDK setup executes the payment creation step in milliseconds, rendering the checkout UI before the user's cursor even leaves the chat input.

Real-Time Order Feeds via MCP Server

The `list_orders` and `get_order` tools feed raw transaction data directly into your streaming UI components. Your agent queries the payment history, parses the JSON payload, and renders order states without triggering full-page refreshes. This setup eliminates loading spinners. The client streams the raw order data as it arrives, letting you update purchase histories and delivery statuses on the fly inside Next.js or React.

Instant Customer Profile Rendering

The `get_customer` and `list_customers` tools let your conversational interface pull buyer records during active support chats. The SDK pipes customer profiles directly into your chat bubbles, matching emails to payment histories instantly. By avoiding heavy client-side state managers, your app loads faster. The agent fetches the exact profile fields needed and streams them into a lightweight UI component.

Setup guide

Set up Dola Checkout 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 Dola Checkout 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 Dola Checkout 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 Dola Checkout. 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 Dola Checkout 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 Dola Checkout MCP in Vercel AI SDK

Use `create_checkout` inside your streamText tool definition. The Vercel AI SDK calls the Dola Checkout MCP server, gets the session URL, and streams it straight to your React component.

Yes, by passing `update_order` to your model's tools array. The agent listens to the user's request, executes the status change, and streams the updated order object back to the UI.

You configure the MCP client with your endpoint token using `createMCPClient`. The Vercel AI SDK handles the transport layer, letting you invoke tools securely without hardcoding merchant keys in your client-side code.

Always call `mcpClient.close()` once your text generation or streaming loop finishes. This prevents memory leaks in your Edge Functions and keeps your serverless execution times low.

Absolutely. This server only touches metadata like customer profiles and checkout sessions inside an isolated V8 sandbox. Your raw credit card numbers never pass through the MCP layer, meaning your PCI compliance boundary remains completely untouched.

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