You're viewing a demo portfolio

Join the waitlist
PRSM

tag_track

Active

Tool of FreqBlog Music Metadata

declared in 1.27.2

Get a compact, HONESTLY-LABELLED tag list for a track — energy / danceability / valence / acousticness / instrumentalness, plus a mood tag and a broad genre tag. It is a tag-shaped projection of the same open-data analysis get_audio_features returns (no audio upload, no extra compute), so it costs the same 1 quota unit, charged only on a served result. The differentiator vs opaque taggers (e.g. Cyanite) is that EVERY tag carries its own `confidence` and `provenance`: - confidence: measured (our Essentia analysis) | derived (MIREX mood from valence+energy) | model-estimated (AcousticBrainz mood SVM probability — research-grade, raw prob in `value`) | catalog-genre (broad catalogue tag, not fine-grained). - provenance: essentia | valence+energy | acousticbrainz | catalog. `value` is the [0,1] score for numeric tags and null for label-only tags (mood category, genre). Provide EXACTLY ONE identifier: `track` (optionally with `artist`), `isrc`, `mbid`, `spotify_id`, or `track_id` (catalog itunes_track_id). The broad, reliable coverage is the MEASURED tags from our Essentia analysis over the analysed catalogue (plus on-demand by name); MBID/ISRC additionally reach 7.5M+ AcousticBrainz recordings WHEN you supply that identifier. Returns { track, count, tags:[{tag, category, value, confidence, provenance}], disclaimer }. For the full numeric feature set use get_audio_features; for nearest tracks use a discovery tool.

Parameters schema

{
  "type": "object",
  "title": "tag_trackArguments",
  "properties": {
    "isrc": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Isrc",
      "default": null,
      "description": "ISRC, e.g. 'USUM71900001'."
    },
    "mbid": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Mbid",
      "default": null,
      "description": "MusicBrainz recording ID (UUID). Tags come from AcousticBrainz for that exact recording."
    },
    "track": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Track",
      "default": null,
      "description": "Track title. Use with `artist` when known. Required field is ONE of track/isrc/mbid/spotify_id/track_id."
    },
    "artist": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Artist",
      "default": null,
      "description": "Artist name. Only used with `track`; improves accuracy."
    },
    "track_id": {
      "anyOf": [
        {
          "type": "string",
          "maxLength": 80
        },
        {
          "type": "null"
        }
      ],
      "title": "Track Id",
      "default": null,
      "description": "Catalog itunes_track_id from a search_catalog or get_audio_features result."
    },
    "spotify_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Spotify Id",
      "default": null,
      "description": "Spotify track ID, 'spotify:track:...' URI, or open.spotify.com URL. Resolves ONLY tracks already mapped to a Spotify ID (~2.4% of the catalog) — prefer track (+artist) or isrc."
    }
  }
}

What this tool wraps· 1 endpoint

min confidence0.700.50

Parent server

FreqBlog Music Metadata

1/7 registries
View full server →
tag_track — FreqBlog Music Metadata — PRSM MCP