Spotify MCP
NPM · @NOVALUX12/SPOTIFY-MCP
Spotify Web API MCP: playback, library, playlists, search, podcasts. Not affiliated with Spotify.
Available components
Last scanned (10 hours ago)
Scores higher than 99% of npm servers
Category Entertainment and Games
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security98
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 32 of 104 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to NovaLux12/spotify-mcp-server). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 17 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability81
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 24249 tokens (~163/item across 148 items; 131 tools + 17 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (8% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 10 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 133 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Checks we ran (16)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 1 Nov 26 +11
- Stability: fail → pass ▲ security
- 25 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 17 to 20.
- 23 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 10 to 14.
- 20 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 0 to 4.
- 19 Oct 26 0
- Stability: fail → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Schema quality: 100 → unverified ▼ functional
- Package version: 3.1.0 → 3.1.1 functional
- 14 Oct 26 +33
- Stability: unverified → fail ▼ security
- Injection markers: unverified → pass ▲ security
- Tool coverage: unverified → 100 ▲ functional
- Schema quality: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- 13 Oct 26 0
- Package version: 3.0.1 → 3.1.0 functional
- 11 Oct 26 −33
- Stability: fail → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Schema quality: 100 → unverified ▼ functional
- Package version: 3.0.1 → 3.1.0 functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Analysed npm/@novalux12/spotify-mcp@3.1.1
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | NovaLux12/spotify-mcp-server |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/NovaLux12/spotify-mcp-server/.github/workflows/publish.yml@refs/tags/v3.1.1 |
| Rekor log index | 3316895548 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha512:2540a1fa4aacf0673c6ff516b98214d6eb33fdc66f31143b60e77a8126ca0dd3b342ca039af3a3f85a91545074c36de9e080ed2ea8d3986235e9e47da |
Background: How many MCP packages publish verified provenance →
Dependencies 104 packages
| Packages resolved | 104 |
|---|---|
| Stale | 32 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
search_history_stats ~86
Analytics over the local search-history sidecar: top queries, type breakdown, recency. Quota: local only (no API).
| Name | Type | Req | Description |
|---|---|---|---|
| response_format | string | – | 'concise' = human prose, 'detailed' = more fields in prose, 'json' = raw API object |
| top_n | integer | – | Top N queries to show (default 10) |
No output schema declared.
No examples provided.
search_saved_albums ~152
Search saved albums (client-side filter over bounded walk). Quota: GET /me/albums paged.
| Name | Type | Req | Description |
|---|---|---|---|
| added_after | string | – | ISO date — only albums added after this |
| artist | string | – | Substring match against album artist |
| max_results | integer | – | Max items to return (default: SPOTIFY_MCP_MAX_ITEMS env or 50) |
| query | string | – | Substring match against album name/artist |
| response_format | string | – | 'concise' = human prose, 'detailed' = more fields in prose, 'json' = raw API object |
| scan_cap | integer | – | Max albums to scan (default fetchAllCap) |
No output schema declared.
No examples provided.
search_saved_audiobooks ~132
Search saved audiobooks (bounded walk + client-side filter). Quota: GET /me/audiobooks paged.
| Name | Type | Req | Description |
|---|---|---|---|
| max_results | integer | – | Max items to return (default: SPOTIFY_MCP_MAX_ITEMS env or 50) |
| query | string | – | Substring against audiobook name/author |
| response_format | string | – | 'concise' = human prose, 'detailed' = more fields in prose, 'json' = raw API object |
| scan_cap | integer | – | Maximum saved items to scan; defaults to SPOTIFY_MCP_FETCH_ALL_CAP |
No output schema declared.
No examples provided.
search_saved_episodes ~140
Search saved episodes (bounded walk + client-side filter). Quota: GET /me/episodes paged.
| Name | Type | Req | Description |
|---|---|---|---|
| max_results | integer | – | Max items to return (default: SPOTIFY_MCP_MAX_ITEMS env or 50) |
| query | string | – | Substring against episode/show name |
| response_format | string | – | 'concise' = human prose, 'detailed' = more fields in prose, 'json' = raw API object |
| scan_cap | integer | – | Maximum saved items to scan; defaults to SPOTIFY_MCP_FETCH_ALL_CAP |
| show | string | – | Substring against show name |
No output schema declared.
No examples provided.
search_saved_shows ~187
Search saved podcast shows (bounded walk + client-side filter). Quota: GET /me/shows paged.
| Name | Type | Req | Description |
|---|---|---|---|
| max_results | integer | – | Max items to return (default: SPOTIFY_MCP_MAX_ITEMS env or 50) |
| query | string | – | Substring match against show name and publisher. Spotify removed `publisher` from show payloads in February 2026, so the publisher half can only match on an app registration created before November 2… |
| response_format | string | – | 'concise' = human prose, 'detailed' = more fields in prose, 'json' = raw API object |
| scan_cap | integer | – | Maximum saved items to scan; defaults to SPOTIFY_MCP_FETCH_ALL_CAP |
No output schema declared.
No examples provided.
search_saved_tracks ~256
Search your Liked Songs (saved tracks) by text query and optional facets — client-side filter over a bounded walk of /me/tracks. For catalog-wide search use search. Reports walk truncation.
| Name | Type | Req | Description |
|---|---|---|---|
| added_after | string | – | ISO date — only tracks added after this date |
| added_before | string | – | ISO date — only tracks added before this date |
| album | string | – | Filter to tracks where album name contains this substring |
| artist | string | – | Filter to tracks where any artist name contains this substring |
| limit | integer | – | Max results to return |
| max_items | integer | – | How many saved tracks to walk (default SPOTIFY_MCP_FETCH_ALL_CAP) |
| max_results | integer | – | Max items to return (default: SPOTIFY_MCP_MAX_ITEMS env or 50) |
| query | string | – | Substring to match against track name, artist name, or album name (case-insensitive). Omit to list by facets/sort only. |
| response_format | string | – | 'concise' = human prose, 'detailed' = more fields in prose, 'json' = raw API object |
| sort_by | string | – | Sort order |
No output schema declared.
No examples provided.
search_within_playlist ~272
Text search inside a single playlist: a client-side filter over the rows the walk read, cheaper than paging get_playlist_items yourself for a narrow query — but it can only see that window, so scanned_items/scan_cap/scan_truncated say how much of the playlist was actually read. Matches item name, artist, album and show name; kind narrows a mixed playlist to tracks only or episodes only. Quota: GET /playlists/{id}/items paged.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | – | Alias for playlist_id, matching get_playlist_items |
| kind | string | – | Item kinds to match: 'track', 'episode', or 'any' (default — both). Mixed playlists hold both row shapes |
| market | string | – | Market for track relinking, e.g. 'US' |
| max_results | integer | – | Max items to return (default: SPOTIFY_MCP_MAX_ITEMS env or 50) |
| playlist_id | string | – | Playlist ID (or pass it as 'id') |
| query | string | yes | Substring to match against track/episode name, artist, album, show name |
| response_format | string | – | 'concise' = human prose, 'detailed' = more fields in prose, 'json' = raw API object |
No output schema declared.
No examples provided.
seek ~97
Seek to a position in the current track
| Name | Type | Req | Description |
|---|---|---|---|
| device_id | string | – | Target device ID |
| dry_run | boolean | – | Preview only: describe what would change without performing it. Default false — pass true to preview. |
| position_ms | integer | yes | Position in milliseconds |
| response_format | string | – | 'concise' = human prose, 'detailed' = more fields in prose, 'json' = raw API object |
No output schema declared.
No examples provided.
set_repeat ~107
Set repeat mode: off, context (repeat playlist/album), or track (repeat single track)
| Name | Type | Req | Description |
|---|---|---|---|
| device_id | string | – | Target device ID |
| dry_run | boolean | – | Preview only: describe what would change without performing it. Default false — pass true to preview. |
| response_format | string | – | 'concise' = human prose, 'detailed' = more fields in prose, 'json' = raw API object |
| state | string | yes | Repeat mode |
No output schema declared.
No examples provided.
set_shuffle ~100
Enable or disable shuffle mode
| Name | Type | Req | Description |
|---|---|---|---|
| device_id | string | – | Target device ID |
| dry_run | boolean | – | Preview only: describe what would change without performing it. Default false — pass true to preview. |
| response_format | string | – | 'concise' = human prose, 'detailed' = more fields in prose, 'json' = raw API object |
| state | boolean | yes | true = shuffle on, false = shuffle off |
No output schema declared.
No examples provided.
set_volume ~388
Set playback volume on one device, on a selection of devices, or across every live device. `volume_percent` sets an absolute level; `delta_step` nudges the current level by a signed step. `op` picks the variant: "mute" drops to 0 and remembers the level, "unmute" restores what mute remembered, "preset" applies the per-device presets stored by set_device_volume_preset, and "level" with no volume_percent copies the active device's level to the others. Quota: 1 write for a single device; 1 read + N writes when fanning out.
| Name | Type | Req | Description |
|---|---|---|---|
| all_devices | boolean | – | For op "level" with volume_percent: set every volume-capable device, not a named selection. |
| delta_step | integer | – | Signed nudge, e.g. +10 or -10, clamped to 0–100. Mutually exclusive with volume_percent. |
| device_id | string | – | Device ID for a single-device write (default: the active device) |
| device_ids | array | – | For op "level" with volume_percent: fan out to these device ids or names. Mutually exclusive with all_devices. |
| dry_run | boolean | – | Preview only: describe what would change without performing it. Default false — pass true to preview. |
| exclude_device_id | string | – | For op "level" with no volume_percent: leave this device untouched while levelling the rest |
| op | string | – | Variant: "level" (default) set or copy a level, "mute", "unmute", "preset" |
| response_format | string | – | 'concise' = human prose, 'detailed' = more fields in prose, 'json' = raw API object |
| volume_percent | integer | – | Absolute level 0–100. Mutually exclusive with delta_step. |
No output schema declared.
No examples provided.
show_new_episodes ~436
Find new episodes across your saved podcast shows: reports episodes released within the lookback window (default 7 days), marking which are already saved in your episode library. Fetches /me/shows then each show's latest episodes, overlapping episode lookups (width: SPOTIFY_MCP_MAX_CONCURRENCY, else SPOTIFY_MCP_FANOUT_CONCURRENCY, else 4) so a 25-show scan is not 25 serial round trips. WARNING: M saved shows → M+1 requests (1 show page + M episode lookups). Use max_shows to budget and cost_preview to see the cost without making any calls. This tool is read-only: nothing is ever changed.
| Name | Type | Req | Description |
|---|---|---|---|
| cost_preview | boolean | – | Cost preview only: make no API calls and return the request budget instead of the episode list. Use it to size a real call; it does not report any episodes. Default false. |
| days | integer | – | Lookback window in days. Default 7. |
| market | string | – | ISO 3166-1 alpha-2 country code for the per-show episode lookups, e.g. "US". Defaults to SPOTIFY_MCP_MARKET, then to the account country — these lookups are market-gated, so a wrong default silently… |
| max_results | integer | – | Max items to return (default: SPOTIFY_MCP_MAX_ITEMS env or 50) |
| max_shows | integer | – | Per-call budget for show episode lookups. Default: 25 (or SPOTIFY_MCP_FRESHNESS_BUDGET / SPOTIFY_MCP_SHOWRADAR_BUDGET). Scan caps at min(budget, SPOTIFY_MCP_FETCH_ALL_CAP) and reports truncation. WAR… |
| per_show_limit | integer | – | How many latest episodes to check per show for recency. Default 3. |
| response_format | string | – | 'concise' = human prose, 'detailed' = more fields in prose, 'json' = raw API object |
No output schema declared.
No examples provided.
skip_next ~89
Skip to the next track in the queue or context.
| Name | Type | Req | Description |
|---|---|---|---|
| device_id | string | – | Target device ID |
| dry_run | boolean | – | Preview only: describe what would change without performing it. Default false — pass true to preview. |
| response_format | string | – | 'concise' = human prose, 'detailed' = more fields in prose, 'json' = raw API object |
No output schema declared.
No examples provided.
skip_previous ~99
Skip to the previous track. If more than 3 seconds in, restarts the current track first.
| Name | Type | Req | Description |
|---|---|---|---|
| device_id | string | – | Target device ID |
| dry_run | boolean | – | Preview only: describe what would change without performing it. Default false — pass true to preview. |
| response_format | string | – | 'concise' = human prose, 'detailed' = more fields in prose, 'json' = raw API object |
No output schema declared.
No examples provided.
split_playlist ~112
Split a playlist into N chunks (new playlists). Quota: GET all + N POST /me/playlists + N POST items.
| Name | Type | Req | Description |
|---|---|---|---|
| dry_run | boolean | – | Preview only: validate inputs and describe exactly what would change without performing it |
| name_prefix | string | – | Prefix for new playlist names (default: source name) |
| parts | integer | yes | Number of parts (2–10) |
| playlist_id | string | yes | Source playlist ID |
| public | boolean | – | Public flag for new playlists |
No output schema declared.
No examples provided.
spotify_doctor ~130
Run read-only diagnostics: token presence/expiry, auth-time scopes vs write tools enabled by active toolsets, Premium gating, rate-limit cooldown, config state, visible account details when reachable, and the live registered-tool surface with toolset/scope/READONLY trim causes. The only live request is GET /me; no mutation requests are issued.
| Name | Type | Req | Description |
|---|---|---|---|
| response_format | string | – | 'concise' = human prose, 'detailed' = more fields in prose, 'json' = raw API object |
| verbose | boolean | – | Include per-check technical detail lines when response_format is concise |
Structured output declared, but exposes no named fields.
No examples provided.
start_podcast_session ~349
Plan a podcast session (see plan_podcast_session) and start it on a device. Limitation: Spotify cannot apply resume offsets when queueing — only the first episode can start at its resume point (via PUT /me/player/play on its show context); later episodes are appended to the queue and play from the beginning. With dry_run, nothing is played or queued.
| Name | Type | Req | Description |
|---|---|---|---|
| device_id | string | – | Target device ID; omit for the active device |
| dry_run | boolean | – | Preview only: validate inputs and describe exactly what would change without performing it |
| kind | string | – | Restrict the source: 'episodes' = your saved episodes only, 'shows' = recent episodes of your saved shows only. Omit to use saved episodes (plus saved shows when saved_only is false) |
| market | string | – | ISO 3166-1 alpha-2 country code for the saved-show episode lookups, e.g. "US". Defaults to SPOTIFY_MCP_MARKET, then to the account country — these lookups are market-gated, so a wrong default silentl… |
| max_results | integer | – | Max items to return (default: SPOTIFY_MCP_MAX_ITEMS env or 50) |
| minutes | integer | yes | Session length in minutes (1–480) |
| response_format | string | – | 'concise' = human prose, 'detailed' = more fields in prose, 'json' = raw API object |
| saved_only | boolean | – | When no kind is set, include recent episodes of saved shows too. Default: true (saved episodes only) |
No output schema declared.
No examples provided.
switch_account ~186
Change which registered account this session acts as. Takes effect for every subsequent call in this session: the client re-points its token file, drops the previous account's cached reads and validators, and refuses to switch while a request is in flight. Asks for confirmation first, because every later write then lands in the new account's library. Changes local session state and the account registry only — it issues no Spotify writes.
| Name | Type | Req | Description |
|---|---|---|---|
| profile | string | yes | Profile name to act as — the same value "--profile <name>" takes, or "default" for the account this server started as. The name must already have been authenticated with "spotify-mcp auth --profile <… |
| response_format | string | – | 'concise' = human prose, 'detailed' = more fields in prose, 'json' = raw API object |
No output schema declared.
No examples provided.
tag_management ~179
Declare or retract genre tags for an artist in your local sidecar (~/.spotify-mcp/genre-tags.json), which library_genre_report and filter_by_genre consume. add requires at least one tag; remove drops the listed tags, or the artist entirely when none are listed. Supports dry_run preview.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | add tags to an artist, or remove tags/artist |
| artist | string | yes | Artist name exactly as it appears in your library |
| dry_run | boolean | – | Preview only: validate inputs and describe exactly what would change without performing it |
| response_format | string | – | 'concise' = human prose, 'detailed' = more fields in prose, 'json' = raw API object |
| tags | array | – | Tags to add/remove; omit on remove to drop the artist entirely |
No output schema declared.
No examples provided.
toolset_report ~95
Report the active toolsets and registration modules, plus the live registered tool count — answers "how much surface is exposed right now". Discovery set; always available. Also see find_tool / inspect_tool.
| Name | Type | Req | Description |
|---|---|---|---|
| response_format | string | – | 'concise' (default) = prose bullet list; 'detailed' = the same prose; 'json' = the result payload as parseable JSON text, identical to structuredContent |
Structured output declared, but exposes no named fields.
No examples provided.
transfer_playback ~322
Move playback to a different Spotify Connect device, named by exact id, by the label you gave it, or by a case-insensitive name substring. A plain transfer restarts the track at 0:00 on the target; `preserve_position: true` carries the current track and play position across instead, and `restore_shuffle_repeat: true` re-applies the current shuffle and repeat modes on the target. Quota: 1 read to resolve the device, then 1–4 writes depending on the flags.
| Name | Type | Req | Description |
|---|---|---|---|
| device | string | yes | Target device: exact id, sidecar label, or case-insensitive name substring |
| device_id | string | – | DEPRECATED: use `device` |
| dry_run | boolean | – | Preview only: describe what would change without performing it. Default false — pass true to preview. |
| play | boolean | – | Force play (true) or arrive paused (false); omit to preserve the current play state. With preserve_position, true also resumes a session that is currently paused. |
| preserve_position | boolean | – | Resume the current track at its current position on the target instead of restarting it (default: false) |
| response_format | string | – | 'concise' = human prose, 'detailed' = more fields in prose, 'json' = raw API object |
| restore_shuffle_repeat | boolean | – | Re-apply the current shuffle and repeat modes on the target (default: false) |
| volume | integer | – | Volume to set on the target after transfer, 0–100 |
No output schema declared.
No examples provided.
undo_last_mutation ~119
Undo the most recent reversible mutation (receipt FIFO). Same inversion semantics as undo_mutation: add/save → remove, removal → re-add. Executing needs confirmation and is refused when the client cannot prompt (SPOTIFY_MCP_CONFIRM=never bypasses).
| Name | Type | Req | Description |
|---|---|---|---|
| dry_run | boolean | – | Preview only, and the default: pass dry_run: false to execute the rollback. |
| response_format | string | – | 'concise' = human prose, 'detailed' = more fields in prose, 'json' = raw API object |
No output schema declared.
No examples provided.
undo_mutation ~172
Undo a specific mutation by receipt ID. Inverts the recorded direction: an add/save is undone by removing, a removal by re-adding (playlist items or library). A playlist add undo removes only the rows it created, refusing when no row positions are recorded. The result reflects the refetched post-state. Non-reversible kinds return not reversible. Executing needs confirmation and is refused when the client cannot prompt (SPOTIFY_MCP_CONFIRM=never bypasses).
| Name | Type | Req | Description |
|---|---|---|---|
| dry_run | boolean | – | Preview only, and the default: pass dry_run: false to execute the rollback. |
| receipt_id | string | yes | Receipt ID to undo |
| response_format | string | – | 'concise' = human prose, 'detailed' = more fields in prose, 'json' = raw API object |
No output schema declared.
No examples provided.
unfollow_playlist ~109
Unfollow a playlist — remove it from your Spotify library — via DELETE /me/library. Always asks before writing unless SPOTIFY_MCP_CONFIRM=never.
| Name | Type | Req | Description |
|---|---|---|---|
| dry_run | boolean | – | Preview only: validate inputs and describe exactly what would change without performing it |
| playlist_id | string | yes | Playlist ID to unfollow |
| response_format | string | – | 'concise' = human prose, 'detailed' = more fields in prose, 'json' = raw API object |
| Name | Type | Req | Description |
|---|---|---|---|
| cancelled | boolean | – | – |
| dry_run | boolean | – | – |
| ok | boolean | – | – |
| receipt | string|null | – | – |
No examples provided.
unpin_playlist ~109
DEPRECATED, use unfollow_playlist. This tool never unpinned anything; it has always removed the playlist from your Spotify library via DELETE /me/library.
| Name | Type | Req | Description |
|---|---|---|---|
| dry_run | boolean | – | Preview only: validate inputs and describe exactly what would change without performing it |
| playlist_id | string | yes | Playlist ID to unfollow |
| response_format | string | – | 'concise' = human prose, 'detailed' = more fields in prose, 'json' = raw API object |
| Name | Type | Req | Description |
|---|---|---|---|
| cancelled | boolean | – | – |
| dry_run | boolean | – | – |
| ok | boolean | – | – |
| receipt | string|null | – | – |
No examples provided.
unsave_orphan_tracks ~178
Find saved tracks that appear in no playlist (orphans) and optionally unsave them. Quota: walks library + all playlists (capped). PREVIEWS BY DEFAULT — pass dry_run=false to commit. Removing 10+ orphans additionally requires elicitation confirmation (or SPOTIFY_MCP_CONFIRM=never for automation).
| Name | Type | Req | Description |
|---|---|---|---|
| dry_run | boolean | – | Preview only: perform the read side and return a PLAN without changing anything. Default true — pass dry_run=false to commit. |
| max_remove | integer | – | Max orphans to remove (default 50) |
| response_format | string | – | 'concise' = human prose, 'detailed' = more fields in prose, 'json' = raw API object |
| scan_cap | integer | – | Max saved tracks to scan (default fetchAllCap) |
No output schema declared.
No examples provided.
update_playlist ~100
Update a playlist's name, description, or visibility
| Name | Type | Req | Description |
|---|---|---|---|
| collaborative | boolean | – | New collaborative state |
| description | string | – | New description |
| dry_run | boolean | – | Preview only: validate inputs and describe exactly what would change without performing it |
| id | string | – | Alias for playlist_id |
| name | string | – | New name |
| playlist_id | string | – | Playlist ID |
| public | boolean | – | New public state |
No output schema declared.
No examples provided.
upload_playlist_cover ~108
Replace a playlist's cover image with a base64-encoded JPEG. Requires the ugc-image-upload scope on the Spotify developer dashboard app (plus playlist-modify-public/private); without it Spotify rejects the upload with 403.
| Name | Type | Req | Description |
|---|---|---|---|
| dry_run | boolean | – | Preview only: validate inputs and describe exactly what would change without performing it |
| jpeg_base64 | string | yes | Base64-encoded JPEG file contents (max 256 KB decoded) |
| playlist_id | string | yes | Playlist ID |
No output schema declared.
No examples provided.
verify_receipt ~110
Verify that a previous mutation actually landed on Spotify by looking up its receipt. Receipts are session-scoped: the 100 most recent mutations, in this process only, and lost on restart unless SPOTIFY_MCP_RECEIPTS is set. An unknown or expired id returns isError with found:false — a fact about the lookup, not about the mutation.
| Name | Type | Req | Description |
|---|---|---|---|
| receipt_id | string | yes | Receipt ID copied verbatim from a receipt-bearing mutation result (rcpt_<bootId>-<n>) |
No output schema declared.
No examples provided.
whats_new ~503
Personal new-releases radar: derive what's new from followed artists (new albums/singles) and saved shows (new podcast episodes), replacing the removed browse/new-releases surface. WARNING: the follow list is paged 50 artists per request, so on a COLD read cache the album leg costs ceil(max_artists/50) follow pages PLUS up to max_artists album lookups (#679); a repeat scan inside the cache window re-probes the same canonical request and spends no request (#900). A large library can still exhaust small dev-account quotas in one call. Use max_artists to budget and dry_run to preview the cost before running; dry_run labels its figure a budget bound (it is arithmetic over the budget, not a measurement) and a real call reports the request count it actually issued in `cost`. Decision guide: whats_new for personal follows radar; search_fresh for query-scoped tag:new, search/search_deep for general catalog, search_by_isrc for ISRC-exact.
| Name | Type | Req | Description |
|---|---|---|---|
| days_back | integer | – | Look this many days back when `since` is omitted. Default: 30 |
| dry_run | boolean | – | Preview only: validate inputs and describe exactly what would change without performing it |
| kinds | array | – | Which sources to scan. Default: ['albums','podcasts'] |
| max_artists | integer | – | Per-call budget for artist album lookups (and show episode lookups). Default: 25 (or SPOTIFY_MCP_FRESHNESS_BUDGET). Walk caps at this budget and reports truncation. Independent of SPOTIFY_MCP_FETCH_A… |
| max_results | integer | – | Max items to return (default: SPOTIFY_MCP_MAX_ITEMS env or 50) |
| response_format | string | – | 'concise' = human prose, 'detailed' = more fields in prose, 'json' = raw API object |
| since | – | – | Only include releases on/after this date (YYYY-MM-DD), or 'last-check' to resume from the stored per-kind watermark file (default path ~/.spotify-mcp/freshness.json). Tracked per kind, so a call scop… |
No output schema declared.
No examples provided.
wind_down_status ~72
Read the current or most recent wind-down progress, including per-step failures
| Name | Type | Req | Description |
|---|---|---|---|
| device_id | string | – | Only return status for this device id |
| response_format | string | – | 'concise' = human prose, 'detailed' = more fields in prose, 'json' = raw API object |
No output schema declared.
No examples provided.
How do I install the Spotify MCP server?
Spotify MCP runs locally as an npm package, launched with npx -y @novalux12/spotify-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @novalux12/spotify-mcp
claude mcp add novalux12-spotify-mcp-server -- npx -y @novalux12/spotify-mcp
What is the Spotify MCP server?
Spotify MCP is listed in the public MCP registry as io.github.NovaLux12/spotify-mcp-server. Spotify Web API MCP: playback, library, playlists, search, podcasts. Not affiliated with Spotify. This page covers its npm package (@novalux12/spotify-mcp).
Is the Spotify MCP server safe to use?
Spotify MCP scores 96 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Spotify MCP server expose?
Spotify MCP exposes 131 tools: search, get_saved_tracks, get_saved_albums, get_saved_shows, get_saved_episodes, and 126 more. Their descriptions and schemas cost roughly 23,162 tokens of context every time the server is loaded.
Is the Spotify MCP server still maintained?
Spotify MCP is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Spotify MCP server under?
Spotify MCP declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the Spotify MCP server?
VerifyMCP ran 16 checks on Spotify MCP, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.