Spotify-MCP-Web-And-MCP-Server
Copilot instructions1 starsChanged 7 days agoMITView on GitHub
Always use the registered MCP tools directly for Spotify actions. Never write standalone Python scripts or files to interact with the API when an MCP tool is available. If the user asks to create a playlist, inspect tracks, reorder, shuffle, search, discover music, or do any other Spotify action, check the available MCP tools (including the standard spotify* tools like spotifygetmyplaylists, spotifygetplaylist, spotifycreateplaylist, spotifyaddtoplaylist, spotifyremovefromplaylist, spotifyreorderplaylist, spotifyupdateplaylist, spotifyfollowplaylist, spotifyunfollowplaylist, spotifygetplaylistcover, spotifycheckplaylistfollowers, the Playlist Power Tools: spotifymergeplaylists, spotifysplitplaylistbyartist, spotifydeduplicateplaylist, spotifyexportplaylist, spotifyplaylistdiff,…
We split this copilot-instructions.md into the rules it gives an agent
6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 3
Always use the registered MCP tools directly for Spotify actions.
- Very specific: line 7
Do NOT attempt to write temporary python scripts like make_playlist.py and run them.
- Distinctive: line 13
Before making a playlist for a person (e.g., an actor, director, lyricist, or composer), evaluate if the user's prompt is specific enough.
- Distinctive: line 14
If the prompt is highly specific (e.g., "Make a playlist on Yogaraj Bhat, his movies from early 2000s and till now all the movies songs …
- Distinctive: line 15
If the prompt is vague (e.g., "Make a playlist on Yogaraj Bhat"), DO NOT execute immediately.
- Distinctive: line 19
Only after receiving clarified instructions should you invoke the MCP tools to generate the playlist.
≈ “Common” is an estimate: at least 1 in 5 of the 3,669 Copilot instructions files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Spotify MCP Rules
Always use the registered MCP tools directly for Spotify actions. Never write standalone Python scripts or files to interact with the API when an MCP tool is available.
If the user asks to create a playlist, inspect tracks, reorder, shuffle, search, discover music, or do any other Spotify action, check the available MCP tools (including the standard spotify_* tools like spotify_get_my_playlists, spotify_get_playlist, spotify_create_playlist, spotify_add_to_playlist, spotify_remove_from_playlist, spotify_reorder_playlist, spotify_update_playlist, spotify_follow_playlist, spotify_unfollow_playlist, spotify_get_playlist_cover, spotify_check_playlist_followers, the Playlist Power Tools: spotify_merge_playlists, spotify_split_playlist_by_artist, spotify_deduplicate_playlist, spotify_export_playlist, spotify_playlist_diff, spotify_find_playlist_overlaps, spotify_find_playlist_subsets, spotify_absorb_playlist, the Search, Recommendations & Discovery Tools: spotify_search, spotify_related_artists, spotify_discover_by_artist, spotify_discover_by_mood, spotify_genre_explorer, spotify_discover_deep_cuts, spotify_get_recommendations, the Stats, Analytics & Insights Tools: spotify_top_tracks, spotify_top_artists, spotify_recently_played, spotify_listening_patterns, spotify_taste_profile, spotify_playlist_compare, spotify_playlist_freshness, the Library & Saved Media Tools: spotify_get_saved_tracks, spotify_save_tracks, spotify_remove_saved_tracks, spotify_check_saved_tracks, spotify_get_saved_albums, spotify_save_albums, spotify_remove_saved_albums, spotify_check_saved_albums, the Catalog & Entity Inspection (Browse) Tools: spotify_get_track, spotify_get_album, spotify_get_artist, spotify_get_artist_albums, spotify_get_user, as well as create_actor_playlist, shuffle_playlist, etc.) and call them directly.
Do NOT attempt to write temporary python scripts like make_playlist.py and run them.
[!NOTE] The server supports modular toolsets (
--toolsets=core) with on-demand lazy loading to prevent overloading LLM context windows (~2,757 tokens forcorevs ~21,376 tokens forall). Tools are imported only when invoked. Specify--toolsets=core,playbackor--toolsets=allwhen additional toolsets are needed.
Prompt Clarification Protocol
Before making a playlist for a person (e.g., an actor, director, lyricist, or composer), evaluate if the user's prompt is specific enough.
- If the prompt is highly specific (e.g., "Make a playlist on Yogaraj Bhat, his movies from early 2000s and till now all the movies songs that he wrote"), proceed directly to create it using the MCP tools.
- If the prompt is vague (e.g., "Make a playlist on Yogaraj Bhat"), DO NOT execute immediately. Instead, ask the user clarifying questions tailored to the entity type to get more context.
- For an actor: Ask if they want songs from a specific era, specific co-stars, or their most popular hits.
- For a director/lyricist: Ask if they want songs written/directed in a specific decade, particular blockbusters, or specific music director collaborations.
- For a composer/singer: Ask if they want romantic songs, upbeat tracks, specific eras, or all-time hits. Only after receiving clarified instructions should you invoke the MCP tools to generate the playlist.
Where files are headingNew Copilot instructions files have more rules about branches and pull requests, and fewer about code style.
Of the Copilot instructions files we read, the 2,297 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repositoryOne other file it gives its agents.
- .cursor/rules/spotify-mcp-rules.mdcCursor rule
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

