How to Use the Freesound MCP in Mastra AI

Q: Can my Mastra AI agent search for specific Freesound users and their sounds?

Absolutely. The workflow would first use the getuser tool with a username, then pass the returned user ID into the getusersounds tool to get a list of their uploads.

Q: How do I build a fault-tolerant Freesound downloader with Mastra AI?

Chain the searchsounds and downloadsound tools in a Mastra AI workflow. Mastra's engine will automatically handle retries with exponential backoff if the download fails, ensuring you get the file.

Q: Does the Freesound MCP server let my Mastra AI agent check my own account info?

Yes, the getme tool returns all the details for the authenticated user. You can use this as a first step in a workflow to confirm your credentials are working before performing other actions.

Q: Can I use this to find sounds for a podcast intro?

Yes. Have your agent call searchsounds with a query like "intro music" and a filter for a permissive license. The agent can then downloadsound for the best matches.

Build reliable audio processing workflows on Mastra AI that can find, download, and manage Freesound assets without breaking.

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 Mastra AI

Create your Vinkius account to connect Freesound to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create Resilient Download Bots

The main job is getting the file. Build a Mastra AI workflow that uses `search_sounds` to find an asset, then calls `download_sound`. Mastra's built-in retry logic handles any network hiccups from Freesound's end. You can add conditional steps. If a `download_sound` call fails after three retries, your workflow can automatically send a notification or try searching for an alternative sound. This makes your automation dependable.

Automate Content Moderation with Mastra AI

Build a workflow to manage your team's Freesound uploads. The agent can periodically call `get_pending_uploads` to check the status of new sounds. This is way better than manually checking the website. If a sound is stuck in moderation for too long, your Mastra AI agent can escalate the issue. It can use `get_sound` to pull the metadata and send a detailed alert to a Slack channel or support email.

Your Agent as an Asset Manager

This MCP server lets your agent do more than just fetch files. You can design a workflow that uses `get_user_sounds` to catalog an entire library, calls `get_sound` on each one to check its license, and flags any with restrictive terms. It’s a perfect use case for Mastra AI. The workflow runs in the background, handling thousands of assets and only notifying you when it finds a problem. It's set-and-forget compliance.

Setup guide

Set up Freesound MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Freesound tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "freesound-mcp-client",
  servers: {
    "freesound-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Freesound Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Freesound tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Freesound transactions"
);
console.log(result.text);

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 Mastra AI

Absolutely. The workflow would first use the `get_user` tool with a username, then pass the returned user ID into the `get_user_sounds` tool to get a list of their uploads.

Chain the `search_sounds` and `download_sound` tools in a Mastra AI workflow. Mastra's engine will automatically handle retries with exponential backoff if the download fails, ensuring you get the file.

Yes, the `get_me` tool returns all the details for the authenticated user. You can use this as a first step in a workflow to confirm your credentials are working before performing other actions.

Yes. Have your agent call `search_sounds` with a query like "intro music" and a filter for a permissive license. The agent can then `download_sound` for the best matches.

Your agent's requests for sound metadata and audio files are processed in ephemeral Vinkius sandboxes. The MCP server doesn't store your Freesound OAuth token or any of the data it retrieves for you. Each transaction is isolated and stateless.

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