Magic Master — Audio Mastering

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Audio mastering for AI agents: LUFS/True Peak targets, Suno/Udio AI-fingerprint removal.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "Magic Master — Audio Mastering": {
      "url": "https://magicmaster.pro/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (11)

• get_service_info read-only

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

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• list_presets read-only

  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.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• get_pricing read-only

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

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• check_limits read-only

  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.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• analyze_track read-only

  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.

  Parameters:

  • audio_url (required) — string — 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.

  Hints: read-only yes · destructive no · idempotent not declared · open-world yes

• clean_ai_trace

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

  Parameters:

  • audio_url (required) — string — 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
  • sensitivity — number — 0-1, default server-side.

  Hints: read-only no · destructive no · idempotent not declared · open-world yes

• preview_styles

  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.

  Parameters:

  • audio_url (required) — string — 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.
  • styles — array — Preset keys from list_presets. Default: edm, pop, rnb, standard.

  Hints: read-only no · destructive no · idempotent not declared · open-world yes

• master_track

  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.

  Parameters:

  • audio_url (required) — string — 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.
  • style — string — Preset key from list_presets, e.g. edm, hiphop, podcast, unlimiter. Default standard.
  • bitrate — integer — MP3: 128/192/256/320; OPUS: 128/192.
  • dry_run — boolean — Do not master: report what this call would cost and what settings would apply. Nothing is charged, the file is not even downloaded.
  • intensity — number — 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
  • dither_type — string — Dither for 16-bit WAV output: tpdf (default), ns_e or ns_itu (noise-shaped).
  • target_lufs — number — Override the preset target, e.g. -14 for Spotify.
  • webhook_url — string — Public https URL to POST the result to instead of polling.
  • denoise_strength — number — Noise reduction, 0-1. 0 disables.
  • remove_watermark — boolean — Also remove the Suno/Udio AI fingerprint. Free.
  • restore_dynamics — boolean — Open up a brickwalled source before mastering (pairs with style unlimiter).

  Hints: read-only no · destructive no · idempotent not declared · open-world yes

• batch_master

  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.

  Parameters:

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

  Hints: read-only no · destructive no · idempotent not declared · open-world yes

• get_job read-only

  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.

  Parameters:

  • job_id (required) — string — 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 _ -

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• create_topup_link read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent not declared · open-world yes

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.