How to Use the Belvo MCP in Vercel AI SDK

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

Install the @ai-sdk/mcp package and initialize the client using createMCPClient with your Vinkius endpoint. Then, pass the tools array directly into generateText or streamText to let your agent query financial data.

Q: How does Belvo handle session timeouts in Vercel AI SDK?

Always call mcpClient.close() at the end of your execution block to prevent memory leaks and hanging connections. If a link expires, your agent can call getlink to verify the status and prompt the user.

Feed live Latin American financial data directly into your React components with the Belvo MCP Server and 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 Belvo MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Zero-Latency Financial UI Streams

The `list_accounts` tool lets your agent pull Latin American bank accounts and stream the JSON structure directly into your React components. Your users get tired of staring at loading spinners while fetching banking data. The data renders as it arrives, keeping the interface snappy. You don't need to write custom API wrappers for each bank. Just pass the tools from `mcpClient.tools()` into `streamText` and let your agent query `list_balances` on the fly. It works on Edge Functions, keeping your database connection pool clean and your serverless execution times low.

Real-Time Transaction Feeds in Vercel AI SDK

By calling the `list_transactions` tool, your agent pulls historical financial records and streams them straight to your Vercel AI SDK viewport. Grabbing raw banking data in LatAm used to mean writing complex cron jobs. The SDK handles the streaming buffer so you can show transactions appearing line-by-line. If you need deep details, the agent invokes `get_transaction` to inspect a single charge. You get clean TypeScript types right out of the box, meaning your frontend code knows exactly what fields to expect from Mexican or Brazilian bank feeds.

Direct Owner and Link Verification

The `list_owners` tool lets your agent verify account holder names against your database during user onboarding. Onboarding users requires matching their identity with their bank account. No more manual document uploads or slow batch verifications. The agent manages the entire connection lifecycle using `get_link` over the MCP connection to check if the bank credential is still active. If a link breaks, the frontend UI updates in real-time to prompt the user for a reconnect, avoiding broken state errors.

Setup guide

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

Install the `@ai-sdk/mcp` package and initialize the client using `createMCPClient` with your Vinkius endpoint. Then, pass the tools array directly into `generateText` or `streamText` to let your agent query financial data.

Yes, the SDK handles streaming tool calls so your agent can execute `list_balances` and feed the results straight to your frontend. The UI updates instantly as the bank responds, eliminating the need for loading screens.

Always call `mcpClient.close()` at the end of your execution block to prevent memory leaks and hanging connections. If a link expires, your agent can call `get_link` to verify the status and prompt the user.

You can query any institution supported by the API. Have your agent call `list_institutions` to get a live list of compatible banks and fintechs across Brazil, Mexico, and Colombia.

Vinkius runs this server inside an isolated V8 sandbox, meaning your bank credentials and transaction histories are never cached or exposed. Your API keys are injected securely at runtime and only travel through encrypted tunnels straight to the banking APIs.

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