Freesound

This MCP server provides access to the Freesound API, enabling AI assistants to search, analyze, and retrieve information about audio samples from Freesound.org. It runs locally or within your tooling environment and is invoked by an MCP client to perform a range of Freesound-based operations.

How to use

You use this server by configuring an MCP client to start the Freesound MCP server process and by providing your Freesound API key. Once running, you can perform a variety of actions such as searching for sounds, retrieving sound details, analyzing audio data, finding similar sounds, and accessing user and pack information. The server is started as a local process and communicates with your MCP client through the MCP protocol.

How to install

Prerequisites before you begin:

• Install Node.js 16 or higher
• Obtain a Freesound API key from https://freesound.org/apiv2/apply

Step-by-step installation and startup:

# 1. Clone the project
git clone <repository-url>
cd freesound-mcp-server

# 2. Install dependencies
npm install

# 3. Build the project
npm run build

Configuration and startup instructions

To run the Freesound MCP server locally as an MCP stdio server, you will typically invoke Node with the built bundle and provide your Freesound API key via an environment variable.

{
  "type": "stdio",
  "name": "freesound",
  "command": "node",
  "args": ["/path/to/freesound-mcp-server/dist/index.js"],
  "env": {
    "FREESOUND_API_KEY": "YOUR_API_KEY_HERE"
  }
}

Verifying installation

After starting the server, verify that it is recognized by your MCP client or development tool. You should see the Freesound MCP server listed as active and ready to handle requests.

Additional configuration notes

If you are integrating with Claude Code or Claude Desktop, you will provide the API key in the environment for the MCP server and reference the same startup command in your client configuration. Be sure to keep your API key secure and do not commit it to public repositories.

Tools and endpoints supported

This server exposes a set of endpoints that let you search and retrieve Freesound data, including: search sounds, get sound details, get sound analysis, find similar sounds, get user info, get user sounds, get pack info, and get pack sounds.

Security considerations

Protect your Freesound API key. Use environment variables to supply the key to the MCP server and limit access to the host running the server. Monitor usage to stay within Freesound API rate limits.

Available tools

search_sounds

Search for sounds on Freesound using a text query, with optional filtering, sorting, and pagination.

get_sound

Retrieve detailed information about a specific Freesound sound by its ID, with optional descriptor data.

get_sound_analysis

Fetch audio analysis data for a given sound, with options to select descriptors and normalize values.

get_similar_sounds

Find sounds similar to a reference sound, with optional descriptor filtering and pagination.

get_user

Obtain information about a Freesound user by their username.

get_user_sounds

List sounds uploaded by a specific user with pagination controls.

get_pack

Get information about a Freesound sound pack by its ID.

get_pack_sounds

Retrieve sounds contained in a specific pack with pagination.