# Freqblog Music Metadata MCP server

Source: https://glimind.com/server/mcp-registry%2Fcom.freqblog%2Fmusic-metadata
Registry id: `mcp-registry/com.freqblog/music-metadata`
Status: live (checked 2026-11-22T21:04:01.803Z)

## Verdict

Freqblog Music Metadata MCP server answered 99.94% of Glimind's liveness checks over 30 days, better than 31% of MCP servers, with 657 ms median handshake and 28 outages in 90 days. Its agent-readiness grade is A (97/100) across 15 tools, costing an agent about 7,957 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 99.94% | 31% of MCP servers |
| Median handshake latency | 657 ms | 13% of MCP servers |
| p95 handshake latency | 809 ms | — |
| Checks in 30 days | 6,904 | — |
| Outages, 90 days | 28 | — |
| Median recovery | 6 min | — |
| Agent-readiness score | 97/100 (A) | 88% of MCP servers |
| Tools | 15 | — |
| Tool-list size for an agent | ~7,957 tokens | 24% of MCP servers |
| Days observed | 29 | — |

## Install

```json
{
  "mcpServers": {
    "freqblog-music-metadata-mcp-server": {
      "type": "http",
      "url": "https://mcp.freqblog.com/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http freqblog-music-metadata-mcp-server https://mcp.freqblog.com/mcp
```

## Tools (15)

- `build_setlist`: Order a crate of 2-100 catalog tracks into a beat-matched DJ set that follows an energy arc, keeping each consecutive transition harmonically and tempo-smooth. 
- `discover_tracks`: Find catalog tracks by criteria, with no seed track: tempo, key, genre, release year, chart placement and audio-feature ranges in one call — e.g. house at 122-1
- `find_compatible_keys`: Given a Camelot key (e.g. "8A", "12B"), return the harmonically compatible keys for DJ mixing — the same key, the relative major/minor, and the adjacent +/-1 ke
- `find_similar_tracks`: Tracks that SOUND like one seed track or a set of up to 10, optionally restricted by tempo, key, genre, year, chart or audio-feature ranges — e.g. "like these t
- `find_tracks_by_bpm`: Find catalog tracks near a target tempo. Returns tracks whose BPM is within +/-`tolerance` of `bpm`, ordered by closeness then by an internal catalogue ordering
- `find_tracks_by_key`: Find catalog tracks in a given musical key — for harmonic mixing and key-locked playlists. `key` accepts Camelot ("8A"), Open Key ("1m"), or a key name ("A-Mino
- `get_audio_features`: Get audio features for ONE track — BPM, musical key (name + Camelot + Open Key), energy, danceability, valence, acousticness, loudness, mood, mood_vector, genre
- `get_audio_features_batch`: Get audio features for MANY tracks in one call (up to 50 processed) — ideal for analysing a whole playlist at once. Identify each item by name (`track`/`artist`
- `get_recommendations`: Recommended tracks for one or more seed tracks, in the shape of Spotify's retired GET /v1/recommendations. Takes up to 5 catalog seed tracks and returns catalog
- `get_related_artists`: Artists related to a seed artist, in the shape of Spotify's retired GET /v1/artists/{id}/related-artists. No artist graph exists, so we derive one: build the se
- `score_transition`: Score how well one catalog track mixes into another (0-100) — the pairwise DJ transition score no raw key/BPM API gives you. Combines Camelot-wheel key compatib
- `search_by_description`: Find catalog tracks from a plain-language description of how they sound — e.g. "melancholic piano, slow", "dark ambient strings", "upbeat acoustic guitar, fast"
- `search_catalog`: Full-text search the catalog by any mix of track / artist / album tokens. Use this to resolve a fuzzy, partial, or misspelled name into concrete tracks BEFORE c
- `suggest_next_track`: Given a seed track, return the top-N catalog tracks to play NEXT, ranked by transition score. Each suggestion carries the same `score`, per-component scores and
- `tag_track`: Get a compact, clearly labelled tag list for a track — energy / danceability / valence / acousticness / instrumentalness (instrumental vs vocal, judged on the 3

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.
