FreqBlog Music Metadata

{
  "id": "aix_1e8f25dbb4",
  "name": "FreqBlog Music Metadata",
  "operator": "(unclaimed - source: registry-official · publisher: com.freqblog)",
  "description": "Audio features + harmonic set-building for tracks by name/ISRC. Spotify audio-features replacement.",
  "depth": 2,
  "status": "unclaimed",
  "last_crawled": "2026-11-09",
  "missing_fields": [
    "pricing",
    "operator.identity"
  ],
  "skills": [
    "streaming-tools"
  ],
  "protocols": {
    "mcp": "https://mcp.freqblog.com/mcp",
    "a2a": null
  },
  "pricing": null,
  "regions": [
    "global"
  ],
  "languages": [
    "en"
  ],
  "reputation": {
    "tasks_completed": null,
    "dispute_rate": null,
    "p95_latency_ms": 1857,
    "uptime_30d": 1,
    "onchain_volume_30d_usd": null
  },
  "aix_score": 49,
  "verification": {
    "identity": "none",
    "health": "probe/24h",
    "pricing": "unknown",
    "last_check": "2026-11-09T12:00:33.942Z"
  },
  "pricing_model": "unknown",
  "profile": {
    "mcp_server": "freqblog-music",
    "mcp_version": "1.27.2",
    "tool_count": 15,
    "tools": [
      {
        "name": "get_audio_features",
        "description": "Get audio features for ONE track — BPM, musical key (name + Camelot + Open Key),\n    energy, danceability, valence, acousticness, loudness, mood, mood_vector, genre, time signature, duration and more.\n    `preview_loudness.integrated_lufs` is the BS.1770 integrated loudness (LUFS) of the 30-second\n    preview — often the chorus, so typically a little louder than the full track.\n\n    Fields follow the layout of Spotify's retired /audio-features endpoint.\n    Provide AT LEAST ONE identifier — if you know several, send them all rather than\n    choosing; they resolve by precedence (`track` > `isrc"
      },
      {
        "name": "get_audio_features_batch",
        "description": "Get audio features for MANY tracks in one call (up to 50 processed) — ideal for\n    analysing a whole playlist at once. Identify each item by name (`track`/`artist`), by\n    `isrc` (matched exactly first — best for CJK / K-pop / niche tracks whose fuzzy\n    name-match misses), or both (ISRC first, name as the fallback).\n\n    One bad entry never fails the batch. Items beyond the 50-per-call cap come back with\n    `found: false` and `backfill_status: \"over_limit\"`; an item missing BOTH `track` and\n    `isrc` comes back `\"invalid_no_query\"`. Neither is processed or charged — the response's\n    `s"
      },
      {
        "name": "search_catalog",
        "description": "Full-text search the catalog by any mix of track / artist / album tokens. Use this to\n    resolve a fuzzy, partial, or misspelled name into concrete tracks BEFORE calling\n    get_audio_features.\n\n    Each hit carries `chart_peak`: the best chart position we hold, 1-100 with 100 = a\n    number-one. `null` means no placement we hold — treat that as UNKNOWN, not unpopular,\n    and note it is NOT an audience-size figure. Placements come from the Apple Music and\n    Deezer charts we track (since Aug 2026) and Billboard year-end charts (1960-2025).\n\n    Returns lightweight stubs (itunes_track_id, tr"
      },
      {
        "name": "find_tracks_by_bpm",
        "description": "Find catalog tracks near a target tempo. Returns tracks whose BPM is within\n    +/-`tolerance` of `bpm`, ordered by closeness then by an internal catalogue ordering key (not an audience metric) — useful for DJ set\n    planning, workout playlists, or tempo-matching. Each returned track carries full audio\n    features. To also constrain by musical key, combine with find_tracks_by_key.\n    "
      },
      {
        "name": "find_tracks_by_key",
        "description": "Find catalog tracks in a given musical key — for harmonic mixing and key-locked\n    playlists. `key` accepts Camelot (\"8A\"), Open Key (\"1m\"), or a key name (\"A-Minor\",\n    \"F#-Major\"). Returns tracks ordered by an internal catalogue ordering key (not an audience metric), each with full audio features. To\n    discover which keys mix well with a given key first, use find_compatible_keys.\n    "
      },
      {
        "name": "discover_tracks",
        "description": "Find catalog tracks by criteria, with no seed track: tempo, key, genre, release year,\n    chart placement and audio-feature ranges in one call — e.g. house at 122-126 BPM in 8A or\n    its neighbours with energy above 0.7: min={\"tempo\": 122, \"energy\": 0.7},\n    max={\"tempo\": 126}, key=\"8A\", harmonic=true, genre=\"house\".\n\n    At least one narrowing filter is required (a tempo/feature bound, key, mode, genre, year\n    or chart). Returns `results` (one per recording, each with its bpm, camelot, energy,\n    danceability, valence, acousticness and loudness_db plus catalog metadata),\n    `total_match"
      },
      {
        "name": "find_similar_tracks",
        "description": "Tracks that SOUND like one seed track or a set of up to 10, optionally restricted by\n    tempo, key, genre, year, chart or audio-feature ranges — e.g. \"like these three, but\n    120-128 BPM in 8A or its neighbours\": seed_tracks=[...], min={\"tempo\": 120},\n    max={\"tempo\": 128}, key=\"8A\", harmonic=true.\n\n    Ranked mainly on a PANNs audio embedding (how the recording sounds) blended with an\n    audio-feature similarity. Results are one per recording, with `score`, `genre_relation`\n    to the seed and, with several seeds, `matched_seed`. With filters, results are the\n    closest-sounding tracks "
      },
      {
        "name": "search_by_description",
        "description": "Find catalog tracks from a plain-language description of how they sound — e.g.\n    \"melancholic piano, slow\", \"dark ambient strings\", \"upbeat acoustic guitar, fast\".\n\n    Understands instruments and voice (piano, guitar, acoustic guitar, violin, cello, strings,\n    harp, flute, sax, brass, organ, choir, a cappella, rap, 808/drum machine, orchestral),\n    mood (sad/melancholic, dark/eerie, angry, ambient, happy/upbeat, chill/relaxed),\n    character (acoustic, instrumental, with vocals, energetic, soft, danceable), tempo\n    (slow <= 95 BPM, mid-tempo, fast >= 125 BPM, applied as filters) and an"
      },
      {
        "name": "find_compatible_keys",
        "description": "Given a Camelot key (e.g. \"8A\", \"12B\"), return the harmonically compatible keys for DJ\n    mixing — the same key, the relative major/minor, and the adjacent +/-1 keys on the\n    Camelot wheel. With `extended=true` also returns the +7/-7 energy-boost / energy-drop\n    keys. Pure music theory — no catalog lookup and no quota cost. Pair with find_tracks_by_key\n    to then pull actual tracks in each compatible key.\n    "
      },
      {
        "name": "score_transition",
        "description": "Score how well one catalog track mixes into another (0-100) — the pairwise DJ transition\n    score no raw key/BPM API gives you. Combines Camelot-wheel key compatibility, octave-aware\n    BPM proximity (half/double-time counts as a match), and energy smoothness.\n\n    Returns the overall `score`, per-component scores (`harmonic`/`tempo`/`energy`), a `detail`\n    block (key_relation, both Camelot keys, both BPMs, bpm_delta, bpm_octave_matched, both\n    energies, energy_delta), and a one-line human `reason` (e.g. \"8A->9A adjacent (+1), 126->128\n    BPM (+2), energy +0.04 — clean uplifting mix\"). "
      },
      {
        "name": "suggest_next_track",
        "description": "Given a seed track, return the top-N catalog tracks to play NEXT, ranked by transition\n    score. Each suggestion carries the same `score`, per-component scores and human `reason` as\n    score_transition (e.g. \"11B->11B same key, 118->117 BPM (-0.29), energy +0.12\"), plus its\n    `genre` and `genre_relation` to the seed. GENRE-AWARE by default (cross_genre=auto): off-genre\n    picks that only coincidentally share the seed's key/BPM sink to the bottom — use\n    cross_genre=strict for same-genre-family only, or allow for the old harmonic-only ranking. It\n    is the seed's sonic neighbours re-ran"
      },
      {
        "name": "build_setlist",
        "description": "Order a crate of 2-100 catalog tracks into a beat-matched DJ set that follows an energy\n    arc, keeping each consecutive transition harmonically and tempo-smooth. `arc` is one of\n    peak_time (default — builds to a peak then eases), warmup, cooldown, or flat.\n\n    Returns the `arc`, `count`, an overall `flow_score` (0-100), the `tracks` in play order, the\n    per-step `transitions` ({from_index, to_index, score, reason}), and `omitted` (ids not found\n    in the catalog, or with no audio features on file yet). Feed tracks[].itunes_track_id into a Rekordbox/Serato export to drop the set\n    st"
      },
      {
        "name": "get_recommendations",
        "description": "Recommended tracks for one or more seed tracks, in the shape of Spotify's retired\n    GET /v1/recommendations. Takes up to 5 catalog seed tracks and returns catalogue tracks that\n    sound like the set as a whole — ranked on the same similarity as find_similar_tracks (mainly a\n    PANNs audio embedding, blended with audio features), RE-RANKED by genre affinity (so a\n    close-sounding cross-genre track doesn't outrank same-genre picks).\n\n    Returns `seeds` (each {id, found}), `count`, and `tracks` (each {track, score,\n    genre_relation}; each track carries its `genre`). `genre_relation` is \""
      },
      {
        "name": "get_related_artists",
        "description": "Artists related to a seed artist, in the shape of Spotify's retired\n    GET /v1/artists/{id}/related-artists. No artist graph exists, so we derive one: build the\n    seed artist's track-vector centroid, take its nearest catalogue tracks, aggregate by artist\n    (each scored on its top-3 track similarities so a prolific artist can't dominate) plus a\n    same-genre lift and a cross-genre penalty.\n\n    Returns `artist`, `count`, and `related` (each {artist_name, score, match_count,\n    sample_track_id}). Pass a sample_track_id straight to get_audio_features or\n    suggest_next_track. Costs 2 quot"
      },
      {
        "name": "tag_track",
        "description": "Get a compact, clearly labelled tag list for a track — energy / danceability / valence /\n    acousticness / instrumentalness (instrumental vs vocal, judged on the 30-second\n    preview), plus a mood tag and a broad genre tag. It is a tag-shaped\n    projection of the same open-data analysis get_audio_features returns (no audio upload, no extra\n    compute), so it costs the same 1 quota unit, charged only on a served result.\n\n    EVERY tag carries its own `confidence` and `provenance`:\n      - confidence: measured (a numeric audio feature, source in provenance) | derived (MIREX mood from valence"
      }
    ],
    "profiled_at": "2026-11-09T12:00:33.942Z"
  },
  "unreachable": false
}