yt-dj-mcp
Syncs liked songs from YouTube Music, enriches them with DJ metadata (BPM, key, Camelot key, genre), and creates playlists from saved previews.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@yt-dj-mcp Sync my liked songs and enrich 25 tracks with BPM and key"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
yt-dj-mcp
Local YouTube Music DJ crate MCP server.
The server syncs liked songs from YouTube Music, stores approximate DJ metadata such as BPM, key, Camelot key, and genre, then creates playlists only from saved previews.
Who This Is For
Use this if you have a large YouTube Music liked-song library and want a local, agent-friendly way to turn it into DJ crates. The workflow is deliberately preview-first: inspect candidates locally, then create playlists only after you approve a saved preview.
Related MCP server: navidrome-mcp
What It Can Do
Sync YouTube Music liked songs into local SQLite.
Analyze short local audio sections with
yt-dlp,ffmpeg, and Essentia.Store BPM, musical key, Camelot key, confidence, and source.
Search tracks by BPM/key/genre.
Save playlist previews before writing to YouTube Music.
Create YouTube Music playlists from reviewed previews.
Safety
Uses OAuth by default.
Stores secrets in
~/.config/yt-dj-mcp/.Never prints credential file contents.
Creates playlists only from saved previews.
Browser/HAR auth is an explicit fallback and stores session headers in
browser.json; keep it local and never commit it.Runtime state is local-only. Do not publish
library.sqlite, HAR files, browser headers, OAuth tokens, or downloaded audio.
Quick Start
git clone https://github.com/YOUR_USERNAME/yt-dj-mcp.git
cd yt-dj-mcp
python -m venv .venv
. .venv/bin/activate
pip install -e ".[dev,audio]"
pytest -qAdd the MCP server to your client:
[mcp_servers.yt_dj_mcp]
command = "/absolute/path/to/yt-dj-mcp/.venv/bin/yt-dj-mcp"
args = ["serve"]OAuth Setup
Create a Google Cloud OAuth client that can be used by ytmusicapi, then run:
yt-dj-mcp setup-auth
yt-dj-mcp auth-statusIf OAuth token creation succeeds but YouTube Music requests return HTTP 400, use the explicit local browser fallback:
ytmusicapi browser --file ~/.config/yt-dj-mcp/browser.json
chmod 600 ~/.config/yt-dj-mcp/browser.json
yt-dj-mcp auth-statusIf copying request headers from DevTools is unreliable, export a Chrome Network HAR and import it:
yt-dj-mcp import-har /path/to/music.youtube.com.har
yt-dj-mcp auth-statusbrowser.json contains browser session headers. Keep it local and never commit it.
Commands
yt-dj-mcp setup-auth
yt-dj-mcp auth-status
yt-dj-mcp import-har /path/to/music.youtube.com.har
yt-dj-mcp enrich-tracks --limit 25
yt-dj-mcp reset-auth
yt-dj-mcp serveMCP tools exposed by the server:
auth_statussetup_auth_instructionssync_liked_songslist_liked_songsenrich_tracksfind_dj_candidatescreate_playlist_previewget_playlist_previewcreate_youtube_music_playlistupdate_track_metadata
Audio Metadata Enrichment
enrich-tracks fills missing BPM/key/Camelot metadata by downloading a short
audio section with yt-dlp, analyzing it with Essentia, then caching the
analysis under ~/.config/yt-dj-mcp/audio-metadata-cache/.
Required local commands/packages:
ffmpeg -version
python -m yt_dlp --version
python -c "import essentia; print(essentia.__version__)"The command is best run in small batches:
yt-dj-mcp enrich-tracks --limit 10
yt-dj-mcp enrich-tracks --limit 50If yt-dlp or Essentia is missing, enrichment will leave tracks in the
missing count instead of crashing the server. Use this only for music you are
allowed to process locally; downloading streamed audio may be restricted by the
service's terms.
First Crate Workflow
Run
yt-dj-mcp setup-auth.Run
yt-dj-mcp auth-status.Add the MCP server to Codex or Claude.
Call
sync_liked_songs.Run
yt-dj-mcp enrich-tracks --limit 25or call MCPenrich_tracks.Call
find_dj_candidates.Call
create_playlist_preview.Review with
get_playlist_preview.Create the YouTube Music playlist with
create_youtube_music_playlist.
Suggested Agent Prompt
After installing the MCP server, try:
Sync my YouTube Music liked songs, enrich 50 tracks with BPM/key metadata, then
create 12-track DJ playlist previews grouped by compatible BPM and Camelot key.Review previews before asking the agent to create real YouTube Music playlists.
Limitations
BPM/key values are estimates. Use your ears before playing out.
YouTube Music auth can be brittle. OAuth is preferred, while browser/HAR auth is a local fallback when OAuth does not work.
Audio analysis depends on
ffmpeg,yt-dlp, and Essentia availability.This project does not manage playback and does not provide destructive library operations.
License
MIT
Available Tools
10 toolsauth_statusA
Check OAuth and connection status.
Inputs: no named parameters.
create_playlist_previewC
Create a saved playlist preview.
Inputs: name (required), query (required), candidate_track_ids (required).
create_youtube_music_playlistD
Create a YouTube Music playlist from a preview.
Inputs: preview_id (required), playlist_name (required), description, privacy_status.
enrich_tracksC
Enrich local tracks with DJ metadata.
Inputs: limit, only_missing.
find_dj_candidatesC
Find DJ playlist candidates by BPM/key/genre.
Inputs: key, genre, limit, bpm_max, +3 more.
get_playlist_previewC
Get a saved playlist preview.
Inputs: preview_id (required).
list_liked_songsC
List local liked songs.
Inputs: limit, offset, metadata_status.
setup_auth_instructionsA
Show CLI OAuth setup instructions.
Inputs: no named parameters.
sync_liked_songsC
Sync liked songs into local SQLite.
Inputs: limit.
update_track_metadataC
Manually override DJ metadata for a track.
Inputs: track_id (required), bpm, genre, notes, +2 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 10 tools
Most tools have distinct purposes (auth, syncing, playlist creation, metadata enrichment). Some overlap exists between create_playlist_preview and create_youtube_music_playlist, but they target different artifacts (local preview vs. YouTube Music playlist).
Most tools follow a verb_noun pattern (e.g., enrich_tracks, sync_liked_songs). However, auth_status and setup_auth_instructions deviate slightly, and some names are multi-word nouns. Overall consistent and readable.
10 tools is well-scoped for a server integrating YouTube Music, local SQLite, and DJ metadata. Each tool addresses a core function without unnecessary bloating.
Covers essential workflows: auth, syncing, playlist preview/creation, metadata enrichment, and candidate finding. Minor gaps like missing playlist deletion or track removal, but main DJ tasks are supported.
Maintenance
Related MCP Connectors
Find the tracks DJs play in Instagram, TikTok and set links; ask about your DJs, feed and sets.
Accurate anime-song (anison) database for AI-built playlists — export to Spotify/Apple/YT Music
AI playlist engine that turns music prompts into real YouTube playlists and filters bad versions.
Audio features + harmonic set-building for tracks by name/ISRC. Spotify audio-features replacement.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables managing YouTube Music playlists and searching songs via the YouTube Data API v3, deployed as a free Cloudflare Worker.-
- AlicenseAqualityDmaintenanceEnables building mood-based playlists for Navidrome by joining your library, listen history, and personal playlist labels from Navidrome, ListenBrainz, and Last.fm.15451 npm1AGPL 3.0
- AlicenseNot gradedqualityBmaintenanceEnables DJs to retrieve BPM, key/Camelot, energy, and other track metadata with provider provenance, score transitions, plan setlists, and control Spotify playlists and playback with staged, revalidated writes for safety.MIT
- AlicenseNot gradedqualityBmaintenanceEnables an agent to pull a public or unlisted YouTube playlist with no credentials, infer language, genre and mood tags per track, slice the results into mood-based playlists using declarative YAML rules, and export them as spreadsheets, M3U files or an HTML build console. It also covers publishing, either through quota-aware resumable API jobs or free browser import links, with write operations requiring explicit confirmation and defaulting to dry runs.MIT