How to Use the Freesound MCP in Vercel AI SDK

Q: How do I search Freesound for WAV files using the Vercel AI SDK?

You pass a filter query to the searchsounds tool. Just include filter="type:wav" in your agent's tool call. Your Vercel AI SDK app will then stream only the WAV files it finds.

Q: Can I build a user-facing sound uploader with the Freesound MCP server and the Vercel AI SDK?

Yes. The uploadsound tool lets your agent upload an audio file. After the upload, use describesound to add the necessary metadata.

Q: How does the Vercel AI SDK handle Freesound pack information?

Your agent can call the getpack tool with a pack ID. The Vercel AI SDK will stream the pack's metadata, like its name and list of included sound IDs, right into your UI.

Q: What's the best way to get a user's sound library from Freesound?

Use the getusersounds tool with a user's ID. You can get that ID by first calling getuser with their username.

Stream Freesound search results and audio data directly into your Next.js app with the Vercel AI SDK. No more loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Freesound MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Search in Your UI

Use `search_sounds` to find audio clips and stream the results directly into your React components. Your users see sound names, descriptions, and tags appear in real-time as your agent finds them. It's a much better experience than waiting for a full list to load. Once a user finds a sound they like, you can use `get_sound` to fetch its detailed metadata—license, duration, sample rate—and instantly update the UI. This MCP Server makes your app feel alive with data.

Manage User Content

This isn't just for pulling data. Let users manage their own Freesound assets through your interface. Your agent can call `get_pending_uploads` to show them which of their sounds are still in moderation. From there, you can build out full user profiles. `get_me` grabs the authenticated user's info, and `get_user_sounds` lists everything they've contributed. It's all there for building a proper front-end experience.

Build Audio Tools with the Vercel AI SDK

Combine tools to create a simple soundboard or sample browser. The flow is straightforward: `search_sounds` to find clips, `get_sound` to check details, and `download_sound` to grab the original file for playback. Since the Vercel AI SDK is built for the edge, these operations are fast. You can build responsive audio tools that feel native, not like a clunky web wrapper around an API.

Setup guide

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

You pass a filter query to the `search_sounds` tool. Just include `filter="type:wav"` in your agent's tool call. Your Vercel AI SDK app will then stream only the WAV files it finds.

Yes. The `upload_sound` tool lets your agent upload an audio file. After the upload, use `describe_sound` to add the necessary metadata.

Your agent can call the `get_pack` tool with a pack ID. The Vercel AI SDK will stream the pack's metadata, like its name and list of included sound IDs, right into your UI.

Use the `get_user_sounds` tool with a user's ID. You can get that ID by first calling `get_user` with their username.

The server only touches Freesound data your agent explicitly requests, like sound metadata, user profiles, and the audio files themselves. Vinkius isolates each request in a sandbox, and all connections use your single endpoint token. Your Freesound credentials are not 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