mcp-qobuz
AI-native MCP server for Qobuz that enables searching, browsing, and managing your music library, including favorites, playlists, and current playback.
README
<div align="center">
MCP server for Qobuz — search, browse, and explore your music library via AI.
<a href="https://kud.io/projects/mcp-qobuz">Website</a> · <a href="https://kud.io/projects/mcp-qobuz/docs">Documentation</a>
</div>
Features
- AI-native Qobuz access — exposes Qobuz to any MCP client (Claude Desktop, Claude Code) as tools.
- Search & lookup — search albums, artists, and tracks; fetch full details for any track, album, artist, or playlist by ID.
- Browse your library — list your favourited tracks, albums, and artists, and all your playlists.
- Now playing — read the current track from the Qobuz desktop app (macOS only — the server must run on the same Mac).
- Flexible auth — Keychain locally, or
QOBUZ_TOKEN/QOBUZ_APP_IDenv vars for headless and remote MCP hosts. - Guarded writes — create playlists, add tracks, and update descriptions, gated behind an explicit
confirmflag.
Install
npm install -g @kud/mcp-qobuz
Usage
Add the server to your .mcp.json:
{
"mcpServers": {
"mcp-qobuz": { "command": "npx", "args": ["-y", "@kud/mcp-qobuz"] }
}
}
Auth — local macOS (Keychain)
Credentials are read automatically from the macOS Keychain using the same "qobuz"/"default" entry written by qobuz-cli. Log in once with qobuz login and this server picks them up — no extra configuration needed.
Auth — headless / remote (env vars)
For CI, remote MCP hosts, or any non-Mac environment, pass credentials via the env block in .mcp.json:
{
"mcpServers": {
"mcp-qobuz": {
"command": "npx",
"args": ["-y", "@kud/mcp-qobuz"],
"env": {
"QOBUZ_TOKEN": "your-token",
"QOBUZ_APP_ID": "your-app-id"
}
}
}
}
Env vars take precedence over the Keychain when both are present.
Note: the
now-playingtool is macOS-only — it reads the player state file written by the Qobuz desktop app. It will return an error on any other platform.
Tools
| Tool | Description |
|---|---|
search |
Search Qobuz for albums, artists, and/or tracks |
get-track |
Fetch full track details by ID |
get-album |
Fetch full album details by ID |
get-artist |
Fetch artist biography and discography by ID |
get-playlist |
Fetch a playlist and its tracks by ID |
list-playlists |
List your Qobuz playlists |
list-favourites |
List your favourited tracks, albums, or artists |
now-playing |
Show what the Qobuz desktop app is playing (macOS only) |
create-playlist |
Create a new playlist — requires confirm: true |
add-to-playlist |
Add tracks to a playlist — requires confirm: true |
update-playlist-description |
Update a playlist's description — requires confirm: true |
Development
git clone https://github.com/kud/mcp-qobuz.git
cd mcp-qobuz
npm install
npm run dev
| Command | Description |
|---|---|
npm run dev |
Run the server with tsx (no build step) |
npm run build |
Compile TypeScript to dist/ |
npm test |
Run the Vitest test suite |
npm run inspect:dev |
Open the MCP Inspector against the dev server |
📚 Full documentation → mcp-qobuz/docs
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.