How to Use the Deezer MCP in Vercel AI SDK

Q: How do I stream Deezer track previews using Vercel AI SDK?

You call searchtracks within your stream. The tool returns a direct preview link that you can pipe into a standard HTML5 audio player component.

Q: Can I use Vercel AI SDK to filter Deezer charts by country?

Yes. Pass the country code to getchart inside your tool call configuration. The SDK streams the parsed country-specific track list straight to your UI.

Build music-streaming web interfaces with Vercel AI SDK and live Deezer API data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Deezer MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build real-time music search UIs with Vercel AI SDK

The `search_tracks` tool fetches live Deezer track listings, durations, and audio preview URLs directly into your edge-compatible TypeScript code via this MCP Server. Your web application gets raw JSON data from the music catalog instantly, bypassing slow mid-tier servers. You stream these track lists directly to your frontend components. When your user searches for a song, the Vercel AI SDK renders the title, artist name, and a working 30-second preview player on the screen before the full LLM response finishes generating.

Generate dynamic playlists on the edge

The `get_playlist` and `get_genre_playlists` tools pull curated track lists and creator metadata directly into your React or Next.js application. This MCP Server lets your agent inspect actual user playlist structures to suggest matching music. Because this server runs in a V8 isolate sandbox, your edge functions stay fast and secure. Your frontend displays updated track lists by feeding raw API data into your UI components without any loading spinners.

Pull instant global music charts

The `get_chart` tool grabs the top songs and albums filtered by ISO 3166-1 country codes to show what is trending in specific regions. Your agent maps these regional trends to generate location-specific recommendations. Because this MCP Server handles the heavy lifting, the data flows through the stream, letting you render rich music dashboards on the fly.

Setup guide

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

You call `search_tracks` within your stream. The tool returns a direct preview link that you can pipe into a standard HTML5 audio player component.

Yes. Pass the country code to `get_chart` inside your tool call configuration. The SDK streams the parsed country-specific track list straight to your UI.

Yes, it works fully on the edge. You connect the client using standard HTTP transport, meaning zero Node.js-only library dependencies to slow down your edge functions.

You configure an authProvider during the client initialization step. When your agent calls `get_artist_radio`, the Vinkius platform manages the backend token rotation so your queries never fail.

Your search keywords and metadata requests run inside ephemeral, isolated sandboxes. Vinkius never stores or logs the music queries or artist IDs that pass through the server to your 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