pro.magicmaster/mastering

Est-ce que pro.magicmaster/mastering est sûr ?

Au dernier audit MCP Hub, le serveur MCP « pro.magicmaster/mastering » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 11 outils

• analyze_track≈ 316 tokens

  Measure integrated LUFS, sample peak, duration, sample rate and stereo correlation without processing. Free, a couple of seconds. Run this before choosing a preset. Note: true peak and loudness range are NOT part of this fast pass — they are measured on the result and come back from get_job.

  Paramètres, retour & exemple (1)

  Paramètres

  • audio_url · string · requis
    Public https URL of the audio file (wav/mp3/flac/m4a). A share link to the page works too — Suno/Udio song pages, Google Drive and Dropbox links are resolved to the file automatically.

  Exemple d'appel

  {"name": "analyze_track", "arguments": {"audio_url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"lufs": 1, "channels": 1, "peak_dbfs": 1, "sample_rate": 1, "duration_sec": 1, "true_peak_db": 1, "genre_suggestion": "texte", "stereo_correlation": 1}}

• batch_master≈ 594 tokens

  Master up to 10 tracks in one call with the same settings. Needs N TOKENS for N tracks, or N free runs — not one. album_mode (default true) levels the tracks RELATIVE to each other: the loudest hits the target exactly, the others keep their offsets, so a quiet interlude is not inflated to single level. Limits: 10 tracks, 100 MB per file and 300 MB per call (this server's own caps, for memory) — the account may allow bigger uploads on the site, but not through this channel. A big album takes minutes — send fewer, longer tracks per call rather than all at once. Returns one job id per track — poll each with get_job. Pass dry_run=true to see the price and the settings before anything is spent.

  Paramètres, retour & exemple (8)

  Paramètres

  • style · string · optionnel
    Preset key from list_presets.
  • bitrate · integer · optionnel
    MP3: 128/192/256/320; OPUS: 128/192.
  • dry_run · boolean · optionnel
    Report the price and settings without mastering and without downloading anything.
  • album_mode · boolean · optionnel
    Keep relative loudness between tracks. Default true. Set false for unrelated singles.
  • audio_urls · array · requis
    Public https URLs, in album order.
  • out_format · string · optionnel · wav | wav24 | mp3 | flac | opus | aac
  • target_lufs · number · optionnel
    Target for the LOUDEST track in album mode.
  • remove_watermark · boolean · optionnel
    Also remove the Suno/Udio AI fingerprint. Free.

  Exemple d'appel

  {"name": "batch_master", "arguments": {"audio_urls": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"jobs": [], "tracks": [], "dry_run": true, "job_ids": [], "poll_with": "texte", "would_charge": "texte", "enough_capacity": true, "nothing_was_charged": true, "album_mode_requested": true, "album_offsets_applied": true}}

• check_limits≈ 202 tokens

  What this account may do right now: token balance, free quota left and when it resets, upload cap, whether PRO modules are available. Call before mastering.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "check_limits", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"free": {}, "max_upload_mb": 1, "can_master_now": true, "tokens_balance": 1, "max_upload_mb_via_mcp": 1, "result_retention_days": 1, "max_batch_total_mb_via_mcp": 1}}

• clean_ai_trace≈ 232 tokens

  Strip the AI generator fingerprint without mastering; loudness and tone stay as they are. Free. Returns a job id — poll get_job.

  Paramètres, retour & exemple (3)

  Paramètres

  • audio_url · string · requis
    Public https URL of the audio file (wav/mp3/flac/m4a). A share link to the page works too — Suno/Udio song pages, Google Drive and Dropbox links are resolved to the file automatically.
  • out_format · string · optionnel · wav | wav24 | mp3 | flac | opus | aac
  • sensitivity · number · optionnel
    0-1, default server-side.

  Exemple d'appel

  {"name": "clean_ai_trace", "arguments": {"audio_url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"job_id": "texte"}}

• create_topup_link≈ 184 tokens

  Prepare a token purchase for the human principal. The agent CANNOT complete the payment: the card payment needs the human. Returns the checkout link to hand over, then poll check_limits.

  Paramètres, retour & exemple (1)

  Paramètres

  • pack_id · string · optionnel
    Pack id from get_pricing, e.g. tokens_10.

  Exemple d'appel

  {"name": "create_topup_link", "arguments": {"pack_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"pack": "texte", "packages": [], "next_step": "texte", "checkout_url": "texte", "agent_can_complete": true}}

• get_job≈ 354 tokens

  Status, progress and result metrics (after_lufs, true_peak_db, lra, platform_ready) for a mastering, cleanup or preview job. For previews it returns each style with its loudness and a listen link. When a master is done it also returns download_url — a signed link that works without credentials for about an hour, so an OAuth-connected agent can fetch the file it paid for. Free.

  Paramètres, retour & exemple (1)

  Paramètres

  • job_id · string · requis
    Job id returned by master_track, clean_ai_trace or preview_styles; batch_master returns one per track in job_ids. Not a URL or a filename: 1-64 chars of A-Z a-z 0-9 _ -

  Exemple d'appel

  {"name": "get_job", "arguments": {"job_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"lra": 1, "error": "texte", "status": "texte", "progress": 1, "after_lufs": 1, "result_url": "texte", "download_url": "texte", "true_peak_db": 1, "platform_ready": "texte", "download_url_expires_in": 1}}

• get_pricing≈ 123 tokens

  Live token packs and payment methods. Never quote prices from memory. Free.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_pricing", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"model": "texte", "packages": [], "wallet_url": "texte"}}

• get_service_info≈ 122 tokens

  What Magic Master does, what is free, what costs a token, and where the rules live. Call once at the start of a session.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_service_info", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_presets≈ 207 tokens

  All mastering presets with their target loudness in LUFS. Call this to get the exact preset keys that master_track and batch_master accept. Use preview_styles instead when you want to HEAR 2-6 of them on the actual track before choosing, and get_service_info when you need the wider service manifest rather than the preset list. Free.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_presets", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "presets": []}}

• master_track≈ 660 tokens

  Master one track. COSTS 1 TOKEN when the account has a balance; otherwise it runs on the free quota without PRO modules. Returns a job id immediately — poll get_job (typical 20-60 s, up to 10 min with restoration). The source is fetched by this server, so the ceiling here is 100 MB per file even when the account allows more. Pass dry_run=true first if you want the price and the effective settings before anything is spent.

  Paramètres, retour & exemple (12)

  Paramètres

  • style · string · optionnel
    Preset key from list_presets, e.g. edm, hiphop, podcast, unlimiter. Default standard.
  • bitrate · integer · optionnel
    MP3: 128/192/256/320; OPUS: 128/192.
  • dry_run · boolean · optionnel
    Do not master: report what this call would cost and what settings would apply. Nothing is charged, the file is not even downloaded.
  • audio_url · string · requis
    Public https URL of the audio file (wav/mp3/flac/m4a). A share link to the page works too — Suno/Udio song pages, Google Drive and Dropbox links are resolved to the file automatically.
  • intensity · number · optionnel
    Multiplier on the preset's multiband compression: 1.0 as designed, 0.5 gentler, 1.5 denser. Values outside 0.5-1.5 are clamped.
  • out_format · string · optionnel · wav | wav24 | mp3 | flac | opus | aac
  • dither_type · string · optionnel · tpdf | ns_e | ns_itu
    Dither for 16-bit WAV output: tpdf (default), ns_e or ns_itu (noise-shaped).
  • target_lufs · number · optionnel
    Override the preset target, e.g. -14 for Spotify.
  • webhook_url · string · optionnel
    Public https URL to POST the result to instead of polling.
  • denoise_strength · number · optionnel
    Noise reduction, 0-1. 0 disables.
  • remove_watermark · boolean · optionnel
    Also remove the Suno/Udio AI fingerprint. Free.
  • restore_dynamics · boolean · optionnel
    Open up a brickwalled source before mastering (pairs with style unlimiter).

  Exemple d'appel

  {"name": "master_track", "arguments": {"audio_url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"job_id": "texte", "dry_run": true, "poll_with": "texte", "would_charge": "texte", "tokens_balance": 1, "nothing_was_charged": true}}

• preview_styles≈ 272 tokens

  Master the middle 24 s of the track in 2-6 presets at once and get each one's loudness plus a listen link. FREE (6 per day). Use this instead of guessing a preset, and instead of burning a token to 'try' one.

  Paramètres, retour & exemple (2)

  Paramètres

  • styles · array · optionnel
    Preset keys from list_presets. Default: edm, pop, rnb, standard.
  • audio_url · string · requis
    Public https URL of the audio file (wav/mp3/flac/m4a). A share link to the page works too — Suno/Udio song pages, Google Drive and Dropbox links are resolved to the file automatically.

  Exemple d'appel

  {"name": "preview_styles", "arguments": {"audio_url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"job_id": "texte", "styles": [], "poll_with": "texte", "preview_url_template": "texte"}}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://magicmaster.pro/mcp