How to Use the Buenbit MCP in Vercel AI SDK

Q: Can I stream real-time price tickers using the Buenbit MCP Server and Vercel AI SDK?

Yes, you use getticker or getcryptoprices inside your tool definition block. The SDK streams the market data directly into your React components without requiring a separate polling server.

Q: How do I handle transaction limits in my Buenbit MCP setup with Vercel AI SDK?

You call listlimits before initiating a trade to check the user's profile trade thresholds. This prevents the SDK from attempting to execute orders that exceed exchange rules.

Build reactive crypto frontends that stream Buenbit portfolio updates using the Vercel AI SDK and our managed MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Buenbit MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Buenbit balances to your UI with Vercel AI SDK

The `list_balances` tool fetches your current Buenbit wallet balances directly from the exchange. By pairing this tool with Vercel's streaming capabilities, your interface displays real-time asset updates the millisecond they resolve on the backend. You can also hook up `list_assets` to populate dynamic Buenbit token dropdowns inside your Next.js components. Because the Vercel AI SDK handles the data stream directly, your users skip the loading spinners and see their actual crypto holdings update live on screen.

Fetch spot prices directly inside your streaming components

The `get_crypto_prices` tool pulls universal Buenbit conversion spot rates on demand. When your user asks your Vercel AI SDK chatbot for a quick price check, the SDK grabs the data from the Buenbit MCP Server and pipes it straight into the active text stream. Combining this with `get_ticker` lets you feed specific trading pairs like BTC/ARS or USDC/ARS directly into your Next.js UI. Your Vercel AI SDK client handles the rendering on the edge, keeping latency low while keeping your price feeds accurate.

Instant client-side order execution via conversational UI

The `create_order` tool executes market and limit orders directly on the Buenbit exchange. By integrating this tool with your edge-compatible Vercel AI SDK, your application lets users buy or sell crypto assets through a simple chat interface. If a trade goes wrong, you can immediately fire `cancel_order` to stop a pending Buenbit transaction before it settles. This direct connection ensures fast execution without spinning up heavy backend servers for your Vercel app.

Setup guide

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

Run npm install ai @ai-sdk/mcp to get the core packages. Then, configure createMCPClient with your Vinkius endpoint URL and pass the tools directly to streamText.

Yes, you use get_ticker or get_crypto_prices inside your tool definition block. The SDK streams the market data directly into your React components without requiring a separate polling server.

You call list_limits before initiating a trade to check the user's profile trade thresholds. This prevents the SDK from attempting to execute orders that exceed exchange rules.

Yes, always call mcpClient.close() when your application finishes processing the stream. This prevents dangling SSE or HTTP connections from leaking memory on your edge functions.

Vinkius isolates your exchange credentials inside a zero-trust V8 sandbox that never exposes your keys to the client-side code. Only the executed tool results like balance lists and transaction histories are passed back to your Vercel AI SDK application.

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