Magic Master — Audio Mastering MCP server
pro.magicmaster/masteringmagicmaster.prostreamable-httpv0.5.0Scanned
Audio mastering for AI agents: LUFS/True Peak targets, Suno/Udio AI-fingerprint removal.
11 tools: 6 change things and 5 only read.
- Reads private data · 1
- Reads text others write · 6
- Can send data out · 1
- 3 findings
Tools listed without sign-in. Remote posture
With Anlyon
6 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Magic Master — Audio Mastering MCP server can do
The Magic Master — Audio Mastering MCP server is published by magicmaster.pro, a domain the MCP Registry verified. It has 11 tools. It can create or change data (6 tools: check_limits, clean_ai_trace, preview_styles, master_track and 2 more), but cannot delete data. 5 tools only read.
1 tool reads private data (get_job); 6 tools bring in text other people can write (analyze_track, clean_ai_trace, preview_styles and 3 more); 1 tool can send data out of your system (master_track). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
The fixed checks matched 3 findings (annotation-conflict and credentials-mention). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 18, 2026, version 0.5.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
11 tools
Changes things 6Claude Code: ask
batch_masterMaster up to 10 tracks in one call with the same settings.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
check_limitsWhat this account may do right now: token balance, free quota left and when it resets, upload cap, whether PRO modules are available.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
clean_ai_traceStrip the AI generator fingerprint without mastering; loudness and tone stay as they are.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Strip the AI generator fingerprint without mastering; loudness and tone stay as they are. Free. Returns a job id — poll get_job.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
create_topup_linkPrepare a token purchase for the human principal.Reads text others write1 finding
Why it is in this group
- The name "create_topup_link" says "create": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "create_topup_link" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":true}; The name "create_topup_link" says "create": a word for a change.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
master_trackMaster one track.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.webhook_url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
preview_stylesMaster the middle 24 s of the track in 2-6 presets at once and get each one's loudness plus a listen link.Reads text others write1 finding
Why it is in this group
- The name "preview_styles" says "preview": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "preview_styles" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":true}; The name "preview_styles" says "preview": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
Only reads 5Show 5 read-only tools
analyze_trackMeasure integrated LUFS, sample peak, duration, sample rate and stereo correlation without processing.Reads text others writeNo findings
Why it is in this group
- The name "analyze_track" says "analyze": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
get_jobStatus, progress and result metrics (after_lufs, true_peak_db, lra, platform_ready) for a mastering, cleanup or preview job.Reads private data1 finding
Why it is in this group
- The name "get_job" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "status" and "db": it reads databases.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "..._url — a signed link that works without credentials for about an hour, so an OAuth-connecte..."
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_pricingLive token packs and payment methods.No findings
Why it is in this group
- The name "get_pricing" says "get": a word for reading.
Description, as the server wrote it Live token packs and payment methods. Never quote prices from memory. Free.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_service_infoWhat Magic Master does, what is free, what costs a token, and where the rules live.No findings
Why it is in this group
- The name "get_service_info" says "get": a word for reading.
Description, as the server wrote 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
list_presetsAll mastering presets with their target loudness in LUFS.No findings
Why it is in this group
- The name "list_presets" says "list": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
6 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write6
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__mastering__master_track"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:17 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 6
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://magicmaster.pro/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://magicmaster.pro
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- no
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 6 tools that change things (6 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://magicmaster.pro/mcp: tools/list returned 11 tools to an anonymous client, including check_limits (write), clean_ai_trace (write), preview_styles (write), master_track (write), batch_master (write) and 1 more
Findings
Matches of fixed checks, with the text they matched.
- Warnpreview_styles
The server marks "preview_styles" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":true}; The name "preview_styles" says "preview": a word for reading.
The server marks "create_topup_link" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":true}; The name "create_topup_link" says "create": a word for a change.
- Infoget_job
The description mentions "credentials".
What this check looks forMatched text
description: "..._url — a signed link that works without credentials for about an hour, so an OAuth-connecte..."
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.5.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http mastering https://magicmaster.pro/mcpclaude mcp add --transport http mastering https://magicmaster.pro/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__mastering__get_service_info",
"mcp__mastering__list_presets",
"mcp__mastering__get_pricing",
"mcp__mastering__analyze_track",
"mcp__mastering__get_job"
],
"ask": [
"mcp__mastering__check_limits",
"mcp__mastering__clean_ai_trace",
"mcp__mastering__preview_styles",
"mcp__mastering__master_track",
"mcp__mastering__batch_master",
"mcp__mastering__create_topup_link"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as mastering. Review it before you use it.
Capability tags behind 7 rules
- mcp__mastering__analyze_track untrusted-input
- mcp__mastering__clean_ai_trace untrusted-input
- mcp__mastering__preview_styles untrusted-input
- mcp__mastering__master_track untrusted-input, outbound
- mcp__mastering__batch_master untrusted-input
- mcp__mastering__get_job private-data
- mcp__mastering__create_topup_link untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/pro.magicmaster/mastering/verify?hash=850699afad8f781744c2d2823519efe465b7b7617a7f8a5563dda9b80494d8bf" | jq -e '.changed == false'Pinned hash 850699afad8f, from Nov 18, 2026, 06:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/pro.magicmaster/mastering/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/pro.magicmaster/mastering)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:54 UTC.
Magic Master — Audio Mastering MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Magic Master — Audio Mastering MCP server safe?
- No scan can promise that. What its definitions show: 11 tools, 6 of which can change, send or delete something, and 3 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Magic Master — Audio Mastering MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Magic Master — Audio Mastering MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Magic Master — Audio Mastering MCP server have?
- 11 tools: 6 write, 5 read. check_limits, clean_ai_trace, preview_styles, master_track, batch_master, create_topup_link, get_service_info, list_presets and 3 more.
Does the Magic Master — Audio Mastering MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Magic Master — Audio Mastering MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): master_track.
Has the Magic Master — Audio Mastering MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 18, 2026.