How to Use the CurrencyBeacon MCP in Vercel AI SDK

Q: How do I initialize the CurrencyBeacon MCP Server in a Next.js app using Vercel AI SDK?

Install the @ai-sdk/mcp package and use createMCPClient to connect to the Vinkius endpoint. You then pass the tools from CurrencyBeacon directly into generateText or streamText to let your agent query exchange rates.

Q: Can my Vercel AI SDK agent handle multi-currency conversions using the CurrencyBeacon server?

Yes, your agent can call convertcurrency or getlatestrates in a single session to convert values across multiple global currencies. The SDK streams the calculated outputs straight to your frontend components.

Q: What is the maximum date range my Vercel AI SDK agent can query for historical data?

The gettimeseries tool supports up to 365 days of historical currency data. Your agent can pull this entire range in a single call to build interactive charts.

Stream live currency conversions and historical financial trends directly into your Next.js or React UI using CurrencyBeacon 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 CurrencyBeacon MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream CurrencyBeacon rates live via Vercel AI SDK

Your React users hate waiting for currency rate updates to load. This CurrencyBeacon MCP Server hooks directly into `streamText`, letting you pipe live exchange data from `get_latest_rates` straight to the browser without blocking the main thread. When your Vercel AI SDK agent fetches foreign exchange rates, the raw numbers render on screen immediately as they arrive. By bypassing slow API wrappers, you get instant currency displays that update dynamically.

Run `convert_currency` on Vercel's Edge Network

Edge functions require lightweight tools that do not bloat your bundle. By combining CurrencyBeacon with the Vercel AI SDK, you run fast currency conversion queries via `convert_currency` at the edge closest to your user. This setup avoids heavy node modules by relying on the MCP standard to handle the JSON-RPC communication. Your serverless endpoints stay tiny while still giving your UI immediate access to global currency calculations.

Map `get_timeseries` data directly to React components

Feeding historical currency trends into charts used to require complex backend data pipelines. Now, your Vercel AI SDK agent invokes `get_timeseries` and streams 365 days of rate variations directly into your chart component. Using the SDK's tool-calling capabilities, the UI updates its state the second the CurrencyBeacon server returns the historical exchange metrics. You get immediate, interactive financial visualizations without manual fetch loops.

Setup guide

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

Install the `@ai-sdk/mcp` package and use `createMCPClient` to connect to the Vinkius endpoint. You then pass the tools from CurrencyBeacon directly into `generateText` or `streamText` to let your agent query exchange rates.

Yes, your agent can call `convert_currency` or `get_latest_rates` in a single session to convert values across multiple global currencies. The SDK streams the calculated outputs straight to your frontend components.

Vinkius handles the underlying server scaling, while the SDK handles asynchronous tool calls efficiently. Your application can request live pricing via `get_latest_rates` without hitting typical serverless timeout limits.

The `get_timeseries` tool supports up to 365 days of historical currency data. Your agent can pull this entire range in a single call to build interactive charts.

Your CurrencyBeacon API keys are stored in the secure Vinkius vault and never exposed to the client-side Vercel AI SDK bundle. Only the final, processed exchange rate data is transmitted over the secure, ephemeral MCP connection.

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