How to Use the NachoNacho MCP in Vercel AI SDK

Q: How do I connect the NachoNacho MCP Server to Vercel AI SDK?

Install the @ai-sdk/mcp package. Call createMCPClient with your endpoint URL, then pass the tools directly into generateText or streamText.

Q: Can Vercel AI SDK stream NachoNacho transaction logs into React?

Yes. When your agent calls listtransactions, the SDK streams the parsed JSON directly to your frontend components. The UI renders the rows as the data arrives.

Q: Does the NachoNacho MCP Server support OAuth with Vercel AI SDK?

It does. You pass an authProvider to the MCP client during setup. This handles the token exchange before your agent touches any financial endpoints.

Q: What happens if a card creation fails?

The createcard tool returns an error payload. The SDK catches this and streams the failure state to your UI, so you can show a clear error message instead of failing silently.

Build financial dashboards with Vercel AI SDK where virtual cards and SaaS spend load instantly into your React UI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NachoNacho MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Vercel AI SDK Streams Spend Data Live

Your agent pulls real-time financials using `list_balances` and `list_transactions` directly into the frontend. The Vercel AI SDK streams these tool results straight to your Next.js components. Users watch their SaaS spend populate without staring at a loading spinner. You do not have to write manual polling logic. The MCP Server pipes the raw transaction data through the SDK, rendering charts and balance tables instantly. It feels fast because it actually is fast.

Issue Virtual Cards On Demand

Give your users the ability to spin up payment methods using `create_card` right from your chat interface. They type a request, and your AI client provisions a new virtual card with specific limits. The UI updates the second the API returns the card details. You can also handle modifications without page reloads. If a user needs to adjust a budget, `update_card` pushes the new limit to the backend while the UI reflects the change in real-time.

Kill Zombie Subscriptions

Your app queries `list_subscriptions` to identify forgotten accounts and kill unused software budgets. It immediately executes `freeze_card` to stop the bleeding. The user sees the exact moment the card status flips to suspended. If someone needs that subscription back, `unfreeze_card` restores access instantly. You build the interface. The agent handles the actual money moves behind the scenes.

Setup guide

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

Install the `@ai-sdk/mcp` package. Call `createMCPClient` with your endpoint URL, then pass the tools directly into `generateText` or `streamText`.

Yes. When your agent calls `list_transactions`, the SDK streams the parsed JSON directly to your frontend components. The UI renders the rows as the data arrives.

It does. You pass an `authProvider` to the MCP client during setup. This handles the token exchange before your agent touches any financial endpoints.

The `create_card` tool returns an error payload. The SDK catches this and streams the failure state to your UI, so you can show a clear error message instead of failing silently.

Vinkius runs the MCP Server in an ephemeral V8 isolate sandbox. Your Vercel AI SDK client requests the data, the server executes the tool, and the sandbox dies. We do not store your raw card numbers or transaction histories.

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