MD Studio
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MD StudioPrepare C:/Music/Album for LP2, group by album, and show me the plan before recording."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MD Studio — Make MD discs with AI
Let AI handle the tedious part of making an MD: titles, Japanese readings, track order and groups. MD Studio is a free, open-source Windows app for recording music to MiniDisc through NetMD and Hi-MD. Use it yourself, or connect your AI assistant through MCP or the included CLI.
Download for Windows · User manual · Report a problem

The desktop app follows the system language on first launch and can be switched between English, 日本語 and 简体中文 in Settings.
From a folder of music to a finished MD
Install MD Studio and connect your recorder by USB.
Add your music and choose the recording mode.
Ask AI to organize titles, readings and groups, or edit them yourself.
Review the recording plan and capacity, then start recording.
“Prepare the album in C:/Music/Album for LP2. Use half-width katakana for the Japanese normal titles and the original Japanese for full-width titles. Group by album. Show me the plan before writing.”
Related MCP server: applemusic-mcp
Built for making MDs
AI-assisted tags: an included MD metadata Skill guides your assistant through English/Japanese titles, missing tags, readings and grouping. Review uncertain readings before recording.
NetMD and Hi-MD: reuse established device libraries; available modes and features depend on the recorder and disc.
Clear recording modes: SP, LP2, LP4 and MONO where supported, with capacity preview and progress.
One shared studio: the interface, CLI and MCP use the same device, import queue and tasks.
Set up MCP once: its local address persists across app restarts. Closing the window keeps the app in the system tray.
English, 日本語, 简体中文: choose a language and light or dark theme in Settings.
Local audio processing: audio decoding, conversion and USB transfer run on your PC. No audio-processing server is needed.
What you need
Windows 10/11, 64-bit, a compatible USB recorder, a writable MD and reliable power.
For AI: your own client with local HTTP MCP support, or an assistant able to run local CLI commands. MD Studio does not include an AI model or subscription. Clients that can only reach cloud servers cannot connect directly to localhost.
No source checkout, Node.js or separate encoder installation is needed for the standard desktop workflow. Driver setup includes a verified Zadig installer when WinUSB is needed.
The installer is currently unsigned. Download from this repository's Releases page and compare the published SHA-256 checksum. Real-device testing so far includes the Sony MZ-N920; this is not a claim that every recorder has been tested.
AI, privacy and recording
Enable MCP in AI Creation, copy the full local URL into your client, and export/install the included metadata Skill. The URL contains an access key: keep it private. AI is optional; all regular editing and recording controls remain available.
Audio conversion and device communication stay local. Your AI client may send prompts and metadata to its provider under its own settings. Keep power and USB connected until recording finishes; ending a batch waits for the current track to finish safely.
Read the manual for setup, title rules, groups, CLI examples and troubleshooting.
Open source and credits
MD Studio is based on Web MiniDisc Pro, with thanks to asivery and the NetMD/Hi-MD community. Distributed under GPL-2.0-only. See credits, third-party licenses and contributing. MiniDisc and device names belong to their respective owners; this is an independent project.
This server cannot be deployed
Maintenance
Related MCP Connectors
Memoket — access your recording transcripts, summaries, and key takeaways over MCP.
MCP server for Producer/Riffusion AI music generation
Remote MCP for AI video, image, music and speech generation.
Remote MCP server for AI.TV creators — delegate account operations to your AI agent over MCP.
Related MCP Servers
- AlicenseBqualityDmaintenanceMCP server for Synthesizer V AI Vocal Studio, which allows LLMs to create/edit vocal tracks e.g. adding lyrics to the melody.612Apache 2.0
- AlicenseNot gradedqualityAmaintenanceMCP server for Apple Music that lets AI assistants manage playlists, control playback, and browse the music library.233 PyPI100MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to programmatically edit, analyze, and export audio projects through MCP tools, including multi-track editing, effects, transcription, and semantic search.1-
- AlicenseNot gradedqualityCmaintenanceA comprehensive MCP server that enables AI assistants to control music playback, manage users and access, configure providers, and administer a Music Assistant setup through natural language commands.MIT