How to Use the MusicBrainz MCP in Vercel AI SDK

Q: Can I build a related artist feature for my Next.js app with MusicBrainz and the Vercel AI SDK?

Yes. Your agent can use getartist to fetch an artist's details and then parse the relationships to find associated bands or members. This data can then be used to run new searchartists queries, creating a discovery engine.

Q: Is it possible to find all albums from a specific label using MusicBrainz with the Vercel AI SDK?

Absolutely. Your agent can use the searchlabels tool to find the label's ID, then pass that ID to the browsereleasesbylabel tool. This will stream a list of all releases from that label right into your application.

Q: What's the difference between getrelease and getreleasegroup?

A getreleasegroup call gets you the core album concept—like 'The Dark Side of the Moon'. getrelease targets a specific version, like the 2011 Japanese CD remaster. You'd use the first for general album info and the second for detailed edition data.

Build music discovery apps that feel instant. Stream MusicBrainz data directly into your UI with the 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 MusicBrainz MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Find Any Track, Instantly

Let your users search for music and see results appear character-by-character. Your agent uses the `search_recordings` and `search_artists` tools to find matches in the MusicBrainz database. The results stream directly into your React or Next.js components. No more loading spinners. Once a user picks a track, your agent can pull the full details. It calls `get_release` to fetch the album art, tracklist, and label info. Because you're using the AI SDK, this data populates the UI in real-time, creating a fluid user experience.

Map Out an Artist's Entire Career

Give fans a complete picture of an artist's work. Your AI client can start with a name using `search_artists`, grab the unique ID, and then feed it into `browse_releases_by_artist`. This pulls their entire discography, including release dates and countries. You can build a component that displays an artist's timeline as the data streams in. Use `get_artist` to get their bio and life span, then cross-reference with `get_release_group` to show the evolution from EPs to LPs. It's all handled by this MCP Server, you just build the UI.

Connect Compositions to Recordings

Help users find every version of a specific song. Start by finding the original composition with `search_works`. This gives you the unique ISWC and other metadata about the piece itself, separate from any single recording. From there, your agent can use the work's ID to find all associated recordings with `get_work` and its `inc="recordings"` parameter. This lets you build features that show every cover, remix, and live version of a song, streaming the list right into your app.

Setup guide

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

It streams the data. Instead of waiting for the full API response from this MCP server, the AI SDK sends results from tools like `search_releases` piece-by-piece, so your UI can render them as they arrive.

Yes. Your agent can use `get_artist` to fetch an artist's details and then parse the relationships to find associated bands or members. This data can then be used to run new `search_artists` queries, creating a discovery engine.

Absolutely. Your agent can use the `search_labels` tool to find the label's ID, then pass that ID to the `browse_releases_by_label` tool. This will stream a list of all releases from that label right into your application.

A `get_release_group` call gets you the core album concept—like 'The Dark Side of the Moon'. `get_release` targets a specific version, like the 2011 Japanese CD remaster. You'd use the first for general album info and the second for detailed edition data.

This server only processes public music metadata from MusicBrainz, like artist names, release titles, and track durations. Your Vinkius endpoint token is the only credential needed, and all connections are over TLS. No private user data is ever touched or stored.

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