Navidrome

v1.0.0Communicationstable

Analyze listening patterns, build playlists, find missing albums, discover similar artists via Last.fm, fetch synced lyrics, and explore global radio. Play it all through your speakers via mpv, with a built-in web UI that makes any device with a brow

mcpmcp-servernavidrome
Share:
72
Stars
0
Downloads
0
Weekly
0/5

What is Navidrome?

Navidrome is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to analyze listening patterns, build playlists, find missing albums, discover similar artists via last.fm, fetch synced lyrics, and explore global radio. play it all through your speakers via mpv, with a...

Analyze listening patterns, build playlists, find missing albums, discover similar artists via Last.fm, fetch synced lyrics, and explore global radio. Play it all through your speakers via mpv, with a built-in web UI that makes any device with a brow

This server falls under the Communication category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Analyze listening patterns, build playlists, find missing al

Use Cases

Analyze listening patterns and build playlists from music library.
Discover similar artists via Last.fm and play music through web UI.
Blakeem

Maintainer

LicenseAGPL 3.0
Languagetypescript
Versionv1.0.0
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx navidrome-mcp

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Navidrome

Navidrome MCP is a Model Context Protocol server that connects AI assistants to your self-hosted Navidrome music library, enabling natural-language control over playback, playlist creation, listening analytics, and music discovery. It bridges Navidrome's Subsonic-compatible API with Last.fm for similar-artist discovery, LRCLIB for synced lyrics, and Radio Browser for global internet radio. Audio is streamed locally through mpv, and a built-in web UI lets any browser on your LAN act as a remote control. Use it when you want to ask your AI assistant to build a playlist, find missing albums, or analyze your listening history without leaving your chat interface.

Prerequisites

  • Node.js 18 or later installed (to run via npx)
  • A running Navidrome instance with a valid URL, username, and password
  • mpv media player installed for local audio playback
  • An MCP-compatible client such as Claude Desktop
  • Optional: Last.fm API key for similar-artist discovery and LRCLIB for synced lyrics
1

Install the package

Install the navidrome-mcp package globally via npm so it is available as a command on your PATH.

npm install -g navidrome-mcp
2

Configure the MCP client

Add the navidrome server block to your Claude Desktop (or other MCP client) config file, typically located at ~/Library/Application Support/Claude/claude_desktop_config.json on macOS.

{
  "mcpServers": {
    "navidrome": {
      "command": "npx",
      "args": ["navidrome-mcp"]
    }
  }
}
3

Run the settings configurator

Launch the interactive web-based settings page to enter your Navidrome URL, username, password, and optional API keys. The settings are saved to settings.json and persist across restarts.

npx navidrome-config
4

Set optional API keys for discovery features

In the settings page, enter your Last.fm API key to enable similar-artist discovery and missing-album detection. Add a LRCLIB user agent string to fetch time-synced lyrics. These fields are optional but significantly extend the server's capabilities.

5

Verify playback with mpv

Ensure mpv is installed and accessible on your PATH. Navidrome MCP auto-detects the mpv binary, but you can override the path in settings via the playback.mpvPath key if mpv lives in a non-standard location.

which mpv   # should return a path such as /usr/local/bin/mpv
6

Restart your MCP client

Restart Claude Desktop (or your chosen MCP client) to load the new server configuration. The navidrome server will connect to your library on the first tool call.

Navidrome Examples

Client configuration

Add this block to claude_desktop_config.json to register Navidrome MCP with Claude Desktop.

{
  "mcpServers": {
    "navidrome": {
      "command": "npx",
      "args": ["navidrome-mcp"]
    }
  }
}

Prompts to try

Natural-language prompts that work once the server is connected to your Navidrome library.

- "Play 5 random albums from my starred list"
- "Create a 'Hidden Gems' playlist of 5-star tracks with fewer than 5 plays"
- "Which albums from my top 10 Last.fm artists are missing from my library?"
- "Show my listening stats for the past month and suggest new artists I might like"
- "Find a jazz radio station and add it to my Navidrome stations"
- "Queue everything I've starred from the 90s, sorted by year"

Troubleshooting Navidrome

mpv is not found and playback fails

Install mpv via your package manager (e.g., brew install mpv on macOS) and either ensure it is on your PATH or set the playback.mpvPath key in the navidrome-config settings page to the absolute path of the mpv binary.

Last.fm discovery features return no results

Open the settings page with npx navidrome-config and verify that a valid Last.fm API key is entered. API keys are free and obtained at https://www.last.fm/api/account/create.

The web UI is not reachable from other devices on the LAN

In the settings page, enable the 'Expose on LAN' toggle and ensure webui.host is set to 0.0.0.0 rather than localhost. By default the web UI listens on port 8808.

Frequently Asked Questions about Navidrome

What is Navidrome?

Navidrome is a Model Context Protocol (MCP) server that analyze listening patterns, build playlists, find missing albums, discover similar artists via last.fm, fetch synced lyrics, and explore global radio. play it all through your speakers via mpv, with a built-in web ui that makes any device with a brow It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Navidrome?

Follow the installation instructions on the Navidrome GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Navidrome?

Navidrome works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Navidrome free to use?

Yes, Navidrome is open source and available under the AGPL 3.0 license. You can use it freely in both personal and commercial projects.

Browse More Communication MCP Servers

Explore all communication servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "navidrome-mcp": { "command": "npx", "args": ["-y", "navidrome-mcp"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Navidrome?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides