MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
ONNX Runtime stem separation (Demucs HTDemucs). Separate vocals, drums, bass, other from any audio file. Model auto-downloads from HuggingFace. Companion to mixx-dj-mcp.
MIT ★ 1 -
—
MIT -
Daydream's hosted MCP server: original instrumental songs from words, each with five stems. Listing and client settings.
MIT -
MCP server for Aurora, the AI audio workbench. Your AI agent (Claude, Cursor, or any MCP client) drives music generation, covers, sample manufacturing, 7-stem separation, and DAW-ready stem organization. Files land on disk.
npm MIT -
[ALPHA] Local-first 4-deck DJ + stem-separation studio, no cloud needed. Implements the Storytold craft-app harness - see storytold/artcraft.
Apache-2.0 -
Local music analysis for stems, timing, beats, harmony, lyrics, MIDI and loopable sections for Shorts. https://kieransimkin.co.uk/
pypi MIT -
MCP server for AI music production — MusicGen generation, Demucs stem separation, RVC voice conversion. 8 tools, TypeScript.
MIT ★ 2 -
MCP server for Audial: stem splitting, song analysis with audio features, tags and timed lyrics, mastering, MIDI, music generation, resynthesis to Vital or Serum 2, and vocal synthesis from any MCP client.
pypi MIT -
Official Soundverse MCP server: make AI music in Claude and AI agents. Song generation, vocals, stems, voice cloning, remix.
-
MCP server for Audial's hosted AI audio tools: split stems, master tracks, generate MIDI, build sample packs, generate music and vocals from Claude, Cursor or any MCP client
MIT -
BaZi API for Four Pillars of Destiny charts. Day Master, Ten Gods, hidden stems, Na Yin, and typed day, year and hour conventions echoed back.
MIT -
songforge-mcpgithub.com/xdarkzx/songforge-mcpupdated this year
MCP server for local AI music generation via ACE-Step 1.5, with optional vocal/instrumental stem splitting
pypi Apache-2.0 -
Sheet music, MIDI and stems for any song, inside Claude, ChatGPT, Cursor and other MCP apps. Remote server, no sign-in.
MIT -
Mixxx DJ control via FastMCP — 40+ tools: decks, stems (Demucs), video decks, crates, OSC bridge. Pair with mixxxxx fork. For Cursor / Claude Desktop. Webapp + Tauri.
MIT ★ 11 -
MCP server for SoundCraft (Windows, macOS, Linux): multitrack songs from audio and synth/drum notes, effects, mixdowns with LUFS, stems, MIDI, audio processing. Claude Desktop .mcpb, Sunsam Code, Codex and DeepSeek Harness.
Apache-2.0 -
FORTHoughtgithub.com/MariosAdamidis/FORTHoughtupdated this year
A locally-hosted AI research platform for Physics/STEM labs — MCP tool servers for spectroscopy, XRD, SEM, literature search, and OriginLab automation, built on Open WebUI with AMD ROCm.
★ 7 -
saju-mcp-servergithub.com/heungmangoo-art/saju-mcp-serverupdated this year
Saju from Seoul — Korean Four Pillars (사주) MCP: birth charts, Five Elements, Day Master (일간) profiles, stem/branch reference, compatibility. Deterministic, no API keys. Full readings: sajufromseoul.com
npm MIT -
Generate original AI music tracks via Claude Desktop — MCP server powered by ACE-Step 1.5, with vocal/instrumental stem splitting and reference-style matching. No music software or AI/ML knowledge needed.
Apache-2.0 ★ 13 -
A Linux DJ studio and DAW that a human and an AI agent play together over MCP. Arrangement with mixer and automation, a modular synthesizer with synths, drums and effects, VST3/LV2 hosting, stem separation, live coding, warp. Public beta.
AGPL-3.0 ★ 1 -
🎙️ 免费好用的本地 AI 人声伴奏分离神器!基于 Meta Demucs 模型,一键离线无损提取 人声/伴奏/鼓点/贝斯,不限音频时长、零排队、100% 保护隐私,免装 Python 开箱即用,自带桌面端与 MCP 接口!
MIT -
Magic Master MCP — audio mastering for AI agents: LUFS targets, True Peak limiting, album mastering, restoration, Suno/Udio AI-fingerprint removal. Thin stdio bridge to the hosted server https://magicmaster.pro/mcp
npm MIT