# LLM Jukebox

> Use this tool when you need to build AI-powered music discovery and playback systems that can search, download, and play YouTube music. It solves problems of music acquisition and organization, providing a persistent database of downloaded tracks with metadata and respecting legal considerations around personal use and copyright compliance. With inputs of search queries and outputs of playable audio files, it is ideal for use cases requiring autonomous music collection management and playback control.

Canonical page: https://skillsregistry.net/skills/llm-jukebox  
JSON: https://api.skillsregistry.net/v1/skills/llm-jukebox

## Description

This MCP server enables LLMs to search, download, and play YouTube music through integration with yt-dlp for video downloading and pygame for audio playback. Built with FastMCP and featuring async operations with progress tracking, it provides tools for YouTube music search, MP3 conversion with FFmpeg, local music library management using TinyDB, and basic playback controls including play and stop functionality. The implementation maintains a persistent database of downloaded tracks with metadata like title, artist, duration, and download date, making it valuable for building AI-powered music discovery and playback systems that can autonomously find, acquire, and organize music collections from YouTube while respecting legal considerations around personal use and copyright compliance.

## Trust

- **Trust score (0–1):** 0.97
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/llm-jukebox)
- **Repository:** <https://github.com/jabberjabberjabber/llm-jukebox>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "llm-jukebox"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/llm-jukebox` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/llm-jukebox/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt