Every change Wellknown observed on this MCP server, newest first, with what it was before and what it became. Tool-surface changes carry the definition diff. Nothing here is edited after the fact.
Changed the definition of "get_audio_features_batch"
⟨183 unchanged words⟩ call that collects it is free. For a `found: false` item, `backfill_status` `queued` / `processing` / `deferred` means retry later; `unavailable` is terminal (carries `terminal`, `reason`, `retry_after_days` — treat it as a miss until then); null means no match anywhere. For a single track, use get_audio_features.
Changed the definition of "search_catalog"
⟨59 unchanged words⟩ and note it is NOT an audience-size figure.CoveragePlacementsiscome from the Apple Music and Deezer charts we track (since Aug 2026) and Billboard year-endonly sochartsfar.(1960-2025). Returns lightweight stubs (itunes_track_id, track_name, artist_name, ⟨118 unchanged words⟩
Changed the definition of "get_audio_features"
⟨259 unchanged words⟩ speechiness and liveness are currently null for cataloguetracks.tracks; time_signature is ASSUMED 4 (4/4) on every track, not measured. If a track name is not yet in ⟨93 unchanged words⟩
Changed the definition of "get_audio_features" and "get_recommendations"
⟨178 unchanged words⟩ own analysis, NOT on Spotify's scale: energyisandavalencemodelare models of howenergetic / positive the preview soundsand valence our own raw value, both on our own scales (derive thresholds ⟨165 unchanged words⟩
Changed the definition of "get_audio_features", "get_recommendations" and "tag_track"
⟨178 unchanged words⟩ own analysis, NOT on Spotify's scale: energyandisvalenceaaremodelonof how energetic the preview sounds and valence our own rawscalevalue, both on our own scales (derive thresholds from our values, don't copy ⟨28 unchanged words⟩ et al. 2020, CC BY 4.0); instrumentalness,is a vocal-detection model's score for the 30-second preview (not the whole track); speechiness and liveness are currently null for catalogue
Changed the definition of "build_setlist", "get_audio_features" and "get_recommendations"
⟨61 unchanged words⟩ and `omitted` (ids not found in the catalog, or with no audio features on file yet). Feed tracks[].itunes_track_id into a Rekordbox/Serato ⟨18 unchanged words⟩
⟨178 unchanged words⟩ own analysis, NOT on Spotify's scale: energy,danceabilityandvalence are on
Changed the definition of "get_audio_features" and "tag_track"
⟨15 unchanged words⟩ Key), energy, danceability, valence, acousticness,instrumentalness, liveness, speechiness,loudness, mood, mood_vector, genre, time signature, ⟨77 unchanged words⟩ track ID, URI, or URL (resolved per request by reading the track's title fromourSpotify'sIDpublicmapembedorpagebyand matchingtheittrack'sagainst
Changed the definition of "get_audio_features" and "get_recommendations"
⟨195 unchanged words⟩ the AcousticBrainz classifier where available, else ourestimate;estimateinstrumentalness(beingisreplacedAcousticBrainzbywhereaavailable,newelsemodelnull;sincespeechiness2026-09-27); instrumentalness,
Changed the definition of "get_audio_features" and "get_recommendations"
⟨156 unchanged words⟩ values are present for fully analysed tracks). VALUES are FreqBlog's own analysis, NOT on Spotify's scale: energy, danceability and valence are on our own raw scale (derive thresholds from our values, don't copy Spotify-tuned ones); acousticness is the AcousticBrainz classifier where available, else our estimate; instrumentalness is AcousticBrainz where available, else null; speechiness and liveness are null for our own analyses. If a track name is not yet in ⟨93 unchanged words⟩
⟨291 unchanged words⟩ danceability, duration_ms, energy, instrumentalness, loudness,speechiness,
Changed the definition of "get_recommendations"
⟨290 unchanged words⟩ acousticness, danceability, duration_ms, energy, instrumentalness,liveness,loudness, speechiness, tempo and valence. NOTE: `popularity`was RETIRED(2026-08-27)asanda`liveness`tunable(2026-09-26)onare2026-08-27RETIREDandasnowtunables
Certificate changed, valid to 2026-12-18
Changed the definition of "find_tracks_by_bpm", "find_tracks_by_key", "get_audio_features_batch" and 2 more
⟨13 unchanged words⟩ +/-`tolerance` of `bpm`, ordered by closeness thenpopularityby an internal catalogue ordering key (not an audience metric) — useful for DJ set planning, workout ⟨19 unchanged words⟩
⟨27 unchanged words⟩ , "F#-Major"). Returns tracks ordered bypopularityan internal catalogue ordering key (not an audience metric), each with full audio features. To discover ⟨11 unchanged words⟩
Certificate recorded, valid to 2026-10-20
Authorization not required
First tool surface recorded: 12 tools (server version 1.27.2)
Showing the latest 15 events. The API returns up to 500 and filters by kind: ?kind=tool_surface_changed
⟨338 unchanged words⟩ are FreqBlog's own (not Spotify's): energy(aandmodelvalence (models of how energetic / positive the preview sounds)and valenceon our own scales, danceability/acousticness on AcousticBrainz's ⟨76 unchanged words⟩
⟨337 unchanged words⟩ Values are FreqBlog's own (not Spotify's):energy/valenceenergy (a model of how energetic the preview sounds) and valence on ourrawownscalescales, danceability/acousticness on AcousticBrainz's scale — derive thresholds ⟨72 unchanged words⟩
⟨9 unchanged words⟩ — energy / danceability / valence / acousticness / instrumentalness (instrumental vs vocal, judged on the 30-second preview), plus a mood tag and a broad genretag (instrumentalness is currently null, so it is not tagged).tag. It is a tag-shaped projection of the same ⟨38 unchanged words⟩ `confidence` and `provenance`: - confidence: measured (ouraEssentianumericanalysisaudio feature, source in provenance) | derived (MIREX mood from valence+energy) ⟨15 unchanged words⟩ catalogue tag, not fine-grained). - provenance:essentialibrosa | panns | valence+energy | acousticbrainz | catalog. `value` is the ⟨66 unchanged words⟩ reliable coverage is the MEASURED tags from ourEssentiaown analysis (librosa + a PANNs-based model) over the analysed catalogue(plus on-demand by name); MBID/ISRC additionally reach ⟨34 unchanged words⟩
⟨329 unchanged words⟩ three are returned as null for catalogue tracks.energy/danceability/valenceValues areonFreqBlog'sownscaleown (not Spotify's): energy/valence—on our raw scale, danceability/acousticness on AcousticBrainz's scale — derive thresholds from our values rather than reusingSpotify-tuned ones. e.g. min={"tempo": 100}, ⟨60 unchanged words⟩
⟨79 unchanged words⟩ :track:...' URI, or open.spotify.com URL. ResolvedfromperourrequestSpotify-IDbymapreadingor,theontrack'satitlemiss,frombySpotify's public embed page and matchingtheittrack'sagainsttitleour catalogue (no Spotify IDs are stored) — a title several artists share is ambiguous ⟨62 unchanged words⟩
⟨9 unchanged words⟩ — energy / danceability / valence / acousticness/ instrumentalness, plus a mood tag and a broad genretag.tag (instrumentalness is currently null, so it is not tagged). It is a tag-shaped projection of the same ⟨207 unchanged words⟩
⟨71 unchanged words⟩ :track:...' URI, or open.spotify.com URL. ResolvedfromperourrequestSpotify-IDbymapreadingor,theontrack'satitlemiss,frombySpotify's public embed page and matchingtheittrack'sagainsttitleour catalogue (no Spotify IDs are stored) — a title several artists share is ambiguous ⟨82 unchanged words⟩
⟨289 unchanged words⟩ ), over acousticness, danceability, duration_ms, energy,instrumentalness,loudness, tempo and valence. NOTE: `popularity` (2026-08-27), `liveness`,and`speechiness`(both2026-09-26) and `instrumentalness` (2026-09-27) are RETIRED as tunables and return a 400 —popularitypopularity recorded how a track entered our catalogue, not audience size;livenesstheandotherspeechinessthree are returned as null forour owncatalogueanalyses.tracks. energy/danceability/valence are on FreqBlog's own scale (not ⟨76 unchanged words⟩
⟨175 unchanged words⟩ Attributes: acousticness, danceability, duration_ms, energy,instrumentalness,loudness, tempo, valence.","title":"Min" ⟨124 unchanged words⟩
⟨177 unchanged words⟩ danceability, duration_ms, energy, instrumentalness, loudness,speechiness,tempo, valence.","title":"Min"}," ⟨124 unchanged words⟩
⟨176 unchanged words⟩ acousticness, danceability, duration_ms, energy, instrumentalness,liveness,loudness, speechiness, tempo, valence.","title": ⟨125 unchanged words⟩
⟨161 unchanged words⟩ an ISRC/name with no match anywhere is free. A track you queue and then collect costs ONE unit, not two — the call that collects it is free. For a singletrack, use get_audio_features.
⟨292 unchanged words⟩ duration_ms, energy, instrumentalness, liveness, loudness,popularity,speechiness, tempo and valence. NOTE: `popularity` was RETIRED as a tunable on 2026-08-27 and now returns a 400 — it recorded how a track entered our catalogue, not audience size. The field is still returned. e.g. min={"tempo": 100}, max={ ⟨59 unchanged words⟩
⟨178 unchanged words⟩ duration_ms, energy, instrumentalness, liveness, loudness,popularity,speechiness, tempo, valence.","title":"Min" ⟨124 unchanged words⟩
⟨22 unchanged words⟩ misspelled name into concrete tracks BEFORE calling get_audio_features. Each hit carries `chart_peak`: the best chart position we hold, 1-100 with 100 = a number-one. `null` means no placement we hold — treat that as UNKNOWN, not unpopular, and note it is NOT an audience-size figure. Coverage is Billboard year-end only so far. Returns lightweight stubs (itunes_track_id, track_name, artist_name, ⟨118 unchanged words⟩