Magic Master — Audio Mastering is an MCP server published by pro.magicmaster, hosted at magicmaster.pro. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 11 tools, including get_service_info, list_presets, get_pricing, check_limits, analyze_track.
Audio mastering for AI agents: LUFS/True Peak targets, Suno/Udio AI-fingerprint removal.
2 connections through 5 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
What Magic Master does, what is free, what costs a token, and where the rules live. Call once at the start of a session.
No parameters.
{
"name": "get_service_info",
"title": "Service info",
"description": "What Magic Master does, what is free, what costs a token, and where the rules live. Call once at the start of a session.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"description": "Service manifest: endpoints, presets, live prices, limits, policies."
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
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.
No parameters.
{
"name": "list_presets",
"title": "List mastering presets",
"description": "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.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"presets"
],
"properties": {
"count": {
"type": "integer"
},
"presets": {
"type": "array",
"items": {
"type": "object",
"properties": {
"key": {
"type": "string"
},
"target_lufs": {
"type": "number"
}
}
}
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Live token packs and payment methods. Never quote prices from memory. Free.
No parameters.
{
"name": "get_pricing",
"title": "Get live pricing",
"description": "Live token packs and payment methods. Never quote prices from memory. Free.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"packages"
],
"properties": {
"model": {
"type": "string"
},
"packages": {
"type": "array"
},
"wallet_url": {
"type": "string"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}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.
No parameters.
{
"name": "check_limits",
"title": "Check quota and balance",
"description": "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.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"properties": {
"free": {
"type": "object"
},
"max_upload_mb": {
"type": "integer"
},
"can_master_now": {
"type": "boolean"
},
"tokens_balance": {
"type": "integer"
},
"max_upload_mb_via_mcp": {
"type": "integer",
"description": "effective per-file ceiling for THIS channel"
},
"result_retention_days": {
"type": "integer"
},
"max_batch_total_mb_via_mcp": {
"type": "integer"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}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.
| Parameter | Type | Description |
|---|---|---|
| audio_url * | 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. |
{
"name": "analyze_track",
"title": "Analyze a track",
"description": "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.",
"inputSchema": {
"type": "object",
"required": [
"audio_url"
],
"properties": {
"audio_url": {
"type": "string",
"description": "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."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"properties": {
"lufs": {
"type": [
"number",
"null"
]
},
"channels": {
"type": [
"integer",
"null"
]
},
"peak_dbfs": {
"type": [
"number",
"null"
]
},
"sample_rate": {
"type": [
"integer",
"null"
]
},
"duration_sec": {
"type": [
"number",
"null"
]
},
"true_peak_db": {
"type": [
"number",
"null"
],
"description": "null in the fast pass; see get_job for the measured value"
},
"genre_suggestion": {},
"stereo_correlation": {
"type": [
"number",
"null"
]
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"destructiveHint": false
}
}Strip the AI generator fingerprint without mastering; loudness and tone stay as they are. 1 free run a day, then 1 token per run. Returns a job id — poll get_job.
| Parameter | Type | Description |
|---|---|---|
| audio_url * | 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 | one of ["wav","wav24","mp3","flac","opus","aac"] |
| sensitivity | number | 0-1, default server-side. |
{
"name": "clean_ai_trace",
"title": "Remove Suno/Udio AI fingerprint",
"description": "Strip the AI generator fingerprint without mastering; loudness and tone stay as they are. 1 free run a day, then 1 token per run. Returns a job id — poll get_job.",
"inputSchema": {
"type": "object",
"required": [
"audio_url"
],
"properties": {
"audio_url": {
"type": "string",
"description": "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": {
"enum": [
"wav",
"wav24",
"mp3",
"flac",
"opus",
"aac"
],
"type": "string"
},
"sensitivity": {
"type": "number",
"maximum": 1,
"minimum": 0,
"description": "0-1, default server-side."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"properties": {
"job_id": {
"type": "string"
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"destructiveHint": false
}
}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.
| Parameter | Type | Description |
|---|---|---|
| styles | array | Preset keys from list_presets. Default: edm, pop, rnb, standard. |
| audio_url * | 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. |
{
"name": "preview_styles",
"title": "Compare presets on 24 seconds",
"description": "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.",
"inputSchema": {
"type": "object",
"required": [
"audio_url"
],
"properties": {
"styles": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 6,
"minItems": 2,
"description": "Preset keys from list_presets. Default: edm, pop, rnb, standard."
},
"audio_url": {
"type": "string",
"description": "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."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"properties": {
"job_id": {
"type": "string"
},
"styles": {
"type": "array"
},
"poll_with": {
"type": "string"
},
"preview_url_template": {
"type": "string"
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"destructiveHint": false
}
}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.
| Parameter | Type | Description |
|---|---|---|
| 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. |
| audio_url * | 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. |
| 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 | one of ["wav","wav24","mp3","flac","opus","aac"] |
| 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). |
{
"name": "master_track",
"title": "Master a track",
"description": "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.",
"inputSchema": {
"type": "object",
"required": [
"audio_url"
],
"properties": {
"style": {
"type": "string",
"description": "Preset key from list_presets, e.g. edm, hiphop, podcast, unlimiter. Default standard."
},
"bitrate": {
"type": "integer",
"description": "MP3: 128/192/256/320; OPUS: 128/192."
},
"dry_run": {
"type": "boolean",
"description": "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": {
"type": "string",
"description": "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": {
"type": "number",
"maximum": 1.5,
"minimum": 0.5,
"description": "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": {
"enum": [
"wav",
"wav24",
"mp3",
"flac",
"opus",
"aac"
],
"type": "string"
},
"dither_type": {
"enum": [
"tpdf",
"ns_e",
"ns_itu"
],
"type": "string",
"description": "Dither for 16-bit WAV output: tpdf (default), ns_e or ns_itu (noise-shaped)."
},
"target_lufs": {
"type": "number",
"description": "Override the preset target, e.g. -14 for Spotify."
},
"webhook_url": {
"type": "string",
"description": "Public https URL to POST the result to instead of polling."
},
"denoise_strength": {
"type": "number",
"maximum": 1,
"minimum": 0,
"description": "Noise reduction, 0-1. 0 disables."
},
"remove_watermark": {
"type": "boolean",
"description": "Also remove the Suno/Udio AI fingerprint. Free."
},
"restore_dynamics": {
"type": "boolean",
"description": "Open up a brickwalled source before mastering (pairs with style unlimiter)."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"properties": {
"job_id": {
"type": "string"
},
"dry_run": {
"type": "boolean"
},
"poll_with": {
"type": "string"
},
"would_charge": {
"type": "string"
},
"tokens_balance": {
"type": "integer"
},
"nothing_was_charged": {
"type": "boolean"
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"destructiveHint": false
}
}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.
| Parameter | Type | Description |
|---|---|---|
| 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. |
| audio_urls * | array | Public https URLs, in album order. |
| out_format | string | one of ["wav","wav24","mp3","flac","opus","aac"] |
| target_lufs | number | Target for the LOUDEST track in album mode. |
| remove_watermark | boolean | Also remove the Suno/Udio AI fingerprint. Free. |
{
"name": "batch_master",
"title": "Master an album or a batch",
"description": "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.",
"inputSchema": {
"type": "object",
"required": [
"audio_urls"
],
"properties": {
"style": {
"type": "string",
"description": "Preset key from list_presets."
},
"bitrate": {
"type": "integer",
"description": "MP3: 128/192/256/320; OPUS: 128/192."
},
"dry_run": {
"type": "boolean",
"description": "Report the price and settings without mastering and without downloading anything."
},
"album_mode": {
"type": "boolean",
"description": "Keep relative loudness between tracks. Default true. Set false for unrelated singles."
},
"audio_urls": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 10,
"minItems": 1,
"description": "Public https URLs, in album order."
},
"out_format": {
"enum": [
"wav",
"wav24",
"mp3",
"flac",
"opus",
"aac"
],
"type": "string"
},
"target_lufs": {
"type": "number",
"description": "Target for the LOUDEST track in album mode."
},
"remove_watermark": {
"type": "boolean",
"description": "Also remove the Suno/Udio AI fingerprint. Free."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"properties": {
"jobs": {
"type": "array"
},
"tracks": {
"type": "array",
"description": "job_id, filename, source_url, target_lufs and album_lufs_offset as APPLIED by the server"
},
"dry_run": {
"type": "boolean"
},
"job_ids": {
"type": "array"
},
"poll_with": {
"type": "string"
},
"would_charge": {
"type": "string"
},
"enough_capacity": {
"type": "boolean"
},
"nothing_was_charged": {
"type": "boolean"
},
"album_mode_requested": {
"type": "boolean"
},
"album_offsets_applied": {
"type": "boolean"
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"destructiveHint": false
}
}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.
| Parameter | Type | Description |
|---|---|---|
| job_id * | 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 _ - |
{
"name": "get_job",
"title": "Get job status",
"description": "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.",
"inputSchema": {
"type": "object",
"required": [
"job_id"
],
"properties": {
"job_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_-]{1,64}$",
"maxLength": 64,
"minLength": 1,
"description": "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 _ -"
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"properties": {
"lra": {
"type": [
"number",
"null"
]
},
"error": {
"type": [
"string",
"null"
]
},
"status": {
"type": "string"
},
"progress": {
"type": [
"integer",
"null"
]
},
"after_lufs": {
"type": [
"number",
"null"
]
},
"result_url": {
"type": "string"
},
"download_url": {
"type": "string",
"description": "signed, ~1 h, works without credentials"
},
"true_peak_db": {
"type": [
"number",
"null"
]
},
"platform_ready": {},
"download_url_expires_in": {
"type": "integer"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}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.
| Parameter | Type | Description |
|---|---|---|
| pack_id | string | Pack id from get_pricing, e.g. tokens_10. |
{
"name": "create_topup_link",
"title": "Create a top-up link",
"description": "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.",
"inputSchema": {
"type": "object",
"properties": {
"pack_id": {
"type": "string",
"description": "Pack id from get_pricing, e.g. tokens_10."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"properties": {
"pack": {},
"packages": {
"type": "array"
},
"next_step": {
"type": "string"
},
"checkout_url": {
"type": "string"
},
"agent_can_complete": {
"type": "boolean"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"destructiveHint": false
}
}Audio mastering tools. Analysis, AI-fingerprint cleanup, preset previews and job status are free; a full PRO master costs one token (a batch costs one per track). Payment is completed by the human, not by the agent. Full rules: resource magicmaster://playbook.
Names, descriptions and schemas were written by the server and are shown as data.