Tag-per-Track
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| API_URL | No | Endpoint of the Tag-per-Track analysis API. | https://api.tag-per-track.cloud/api/analyze |
| PRIVATE_KEY | Yes | Private key of your Base burner wallet (66 hex characters starting with 0x). Required but should be a dedicated burner wallet for security. | |
| API_BASE_URL | No | Base endpoint of the Tag-per-Track API for auxiliary routes (e.g. artist stats). | https://api.tag-per-track.cloud/api |
| MAX_SPENDING_USDC | No | Client-side spending cap per request in USDC. | 0.50 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
| prompts | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| analyze_audioA | Analyzes a music track or audio file to extract musical metadata (BPM, genre, mood, key, instruments), AI music detection verdict (HUMAN vs AI_GENERATED Suno/Udio neural vocoder risk with confidence index in 'ai_detection'), explainable A&R scoring v2 in 'arEvaluation' (discovery / signing / beatmaker profiles, AI gate, vocal vs instrumental), and optionally vocal lyrics. Supports local audio files via 'filePath' (read in binary and uploaded) or remote URLs via 'fileUrl'. Cost: 0.15 USDC per track, 0.25 USDC with lyrics, paid per request with an x402 micro-payment on Base. |
| analyze_audio_with_lyricsA | Analyzes an audio track to extract complete musical metadata, AI-generated music detection verdict (HUMAN vs AI_GENERATED Suno/Udio), AND transcribe full vocal lyrics using AI. Supports local audio files via 'filePath' (read in binary and uploaded) or remote URLs via 'fileUrl'. Costs 0.25 USDC per track. (Alias for analyze_audio with extractLyrics: true). |
| triage_demo_folderA | A&R demo inbox triage in ONE call: scans a local folder of demo submissions (.mp3, .wav, .flac, .m4a, .aiff...), analyzes every track, reads the artist/title from audio tags or 'Artist - Title' file names, fetches Spotify traction per artist, applies A&R scoring v2 and returns a COMPACT ranked report (score, priority, bucket, BPM/key/genre, AI-origin flag, monthly listeners, key reason codes, guarded lyrics excerpt). Buckets: 'priority' (listen first), 'listen', 'pass', 'ai_flagged' (confirmed or suspected AI-generated), 'error' (unreadable or rejected file), 'not_analyzed' (the triage stopped early because studio credits ran out or the API key was rejected: see 'halted'). Prefer this tool over analyze_audio_batch whenever the user wants to sort, rank or screen a folder of demos. Cost: 0.15 USDC per track, 0.25 USDC with lyrics, paid per request with an x402 micro-payment on Base. Use dryRun to list files and the estimated cost (estimatedCost.label) without charging. |
| analyze_audio_batchA | Analyzes multiple music tracks or audio files in parallel (batch processing). Vastly reduces total execution time compared to sequential processing. Accepts a list of local file paths ('filePaths') or remote URLs ('fileUrls'), or a structured array of 'tracks'. Cost: 0.15 USDC per track, 0.25 USDC with lyrics, paid per request with an x402 micro-payment on Base. |
| lookup_artist_statsA | Retrieves streaming traction and commercial metrics for an artist (Spotify monthly listeners, followers, popularity score) for A&R qualification. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| qualify_demo_ar | Comprehensive A&R demo evaluation for record labels and music curators. Combines Essentia acoustic analysis (BPM, key, scale, moods, genres, instruments, lyrics) with real-time Spotify streaming traction (monthly listeners, popularity) to produce an A&R Executive Memo with an Emerging Gem verdict. |
| triage_demos | Sorts a local folder of demo submissions like an A&R assistant: one triage_demo_folder call, then a ranked shortlist, AI-generated tracks flagged, and a proposal to file the demos into priority / to-listen / pass / AI sub-folders. |
| batch_demo_screening | Screens an EP, album, or folder of demo submissions in parallel using analyze_audio_batch. Evaluates energy flow, harmonic key progression, and selects standout lead singles. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
analyze_audio, analyze_audio_with_lyrics, and analyze_audio_batch all analyze audio with overlapping metadata/AI detection; analyze_audio_with_lyrics is explicitly an alias, and the batch vs. triage_demo_folder boundary is only clarified by a preference note. Descriptions help distinguish folder-level ranking from parallel analysis, but the redundancy remains confusing.
All tools use snake_case with a verb-first pattern (analyze_audio, triage_demo_folder, lookup_artist_stats), and the analyze_* family is consistently prefixed. No camelCase or mixed conventions appear.
Five tools is well within the ideal 3-15 range for an audio analysis/A&R server. However, analyze_audio_with_lyrics is a redundant alias, so one tool does not fully earn its place, keeping it from a perfect score.
The surface covers single-track analysis, batch analysis, folder triage, lyrics extraction, and artist traction lookup, which covers the core A&R workflow. A minor gap is the lack of any write/tagging operation despite the server name 'Tag-per-Track', and no tool for aggregating or comparing results across tracks.