Magic Master MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MAGICMASTER_MCP_URL | Yes | Magic Master MCP endpoint. Use https://magicmaster.pro/mcp for free tools; https://magicmaster.pro/mcp/oauth also unlocks the paid ones. |
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 | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_service_infoA | What Magic Master does, what is free, what costs a token, and where the rules live. Call once at the start of a session. |
| list_presetsA | All mastering presets with their target loudness in LUFS. Free. |
| get_pricingA | Live token packs and payment methods. Never quote prices from memory. Free. |
| check_limitsA | 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. |
| analyze_trackA | 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. |
| clean_ai_traceA | Strip the AI generator fingerprint without mastering; loudness and tone stay as they are. Free. Returns a job id — poll get_job. |
| preview_stylesA | 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. |
| master_trackA | 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. |
| batch_masterA | 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. |
| get_jobA | 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. |
| create_topup_linkA | Prepare a token purchase for the human principal. The agent CANNOT complete the payment: card and Telegram Stars both need the human. Returns the checkout link to hand over, then poll check_limits. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| master_for_platform | Analyze the track, pick the preset and the platform target, master it, and report LUFS / true peak back. |
| fix_ai_track | Remove the AI fingerprint first, then master with the unlimiter preset if the source is brickwalled. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Mastering passport | Interactive result card: loudness before/after, true peak, range, target deviation and the download link. |
| Agent playbook | Rules for agents using the service. |
| Service manifest | Endpoints, presets, live prices, limits, policies. |
| Terms | Public offer summary and rights. |
TDQS
Scored across 11 tools
Most tools are cleanly separated: analyze_track, clean_ai_trace, preview_styles, master_track, and batch_master all have clearly different purposes. The only mild overlap is among get_service_info, get_pricing, and check_limits, all of which touch cost/account state and require careful reading.
Names are uniformly lowercase snake_case and mostly follow a verb_noun pattern like list_presets, analyze_track, and get_job. The only notable deviation is batch_master, which reads more like a compound noun than the verb_noun pattern used by master_track.
Eleven tools is well within the ideal range and each one earns its place in the mastering workflow. The set covers orientation, presets, pricing, limits, analysis, cleanup, preview, single and batch mastering, job polling, and token purchases without filler.
The full workflow is closed: agents can check limits, analyze, preview, master or batch master, poll for results and downloads, and create a top-up link when tokens run out. There are no dead ends in the core lifecycle.