piano_score
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
pianochart
One audio link in, one playable piano score out: five-line staff images, numbered (jianpu) notation, MusicXML and MIDI, in three tiers that share one arrangement.
audio -> source separation (Demucs) -> melody and bass (pYIN, chroma)
-> arrangement (three tiers) -> staff + numbered notation
What it does and does not do
Transcribes the background music only. Vocals are separated out and dropped.
A drum kit does not become playable piano. Percussion can only show up as rhythmic weight, not as notes.
Non-melodic instruments that carry harmony are folded into the left hand.
Three tiers share one arrangement: same rhythm, same density, same register. Only the key signature differs, so
easyhas the fewest black keys and is the tier to play. Playback restores the original pitch.
Both hands are written to be playable: at most three keys under one hand at a time, never wider than an octave.
Related MCP server: MIDI MCP Server
Install
The pipeline is Python; the DSH plugin is a thin bundle around it. You need both.
git clone https://github.com/regrevia/dsh-pianochart.git
cd dsh-pianochart
# 1. Python environment
python3 -m venv .venv
.venv/bin/pip install -r requirements.txt
brew install cairo # macOS, for cairosvg
# 2. Separation weights, into models/demucs_repo/ (84 MB, not in the repo)
# Demucs normally downloads these; offline you fetch them once:
mkdir -p models/demucs_repo
curl -L -o models/demucs_repo/955717e8-8726e21a.th \
https://huggingface.co/akhaliq/Demucs/resolve/main/955717e8-8726e21a.th
printf "models: ['955717e8']\n" > models/demucs_repo/htdemucs.yamlmodels/demucs_repo/ holds exactly two files: the .th state dict and the
htdemucs.yaml index. Point the pipeline elsewhere with --demucs-repo.
Run the pipeline directly
PYTHONPATH=src .venv/bin/python -m pianochart.cli \
--input track.m4a --preset all --out out/trackOptions: --seconds N analyse only the first N seconds; --no-separate skip
separation for a fast try; --preset easy|medium|hard|all; --transpose N;
--out DIR; --cache-dir DIR; --demucs-repo DIR; --device cpu|mps.
Output per tier in out/<name>/: .musicxml, .mid, .jianpu.txt, -p01.png
staff pages, -roll.png piano roll, and report.json.
Use it from DeepSeek Harness
Install the bundle, then call the host tool piano_score:
{ "source": "https://example.com/track.mp3", "tier": "easy" }sourceis an audio file URL, a local path, or a page URL (the plugin tries to find the audio on it and hands over to Envoy when the page needs a browser).secondsfor a preview of long audio;jianpuCharscaps the numbered notation returned in chat;transposeshifts the written key.Outputs land in a new directory under
out/; the absolute paths come back.
The same pipeline is also served over MCP as piano_score on stdio, so any MCP
client can use it. The bundle starts it from lib/pianochart_mcp.py; point it at
your checkout with PIANOCHART_REPO if it is not next to the plugin.
Reading the numbers
report.json carries the arrangement statistics and two similarity figures
against the source: chroma_cos_mean (tonal agreement over the track) and
chroma_cos_p10 (worst tenth). They measure pitch content, not playability. A
short clip scores lower for lack of material.
What is not done
MuseScore or LilyPond PDF rendering, AMT refinement (Transkun, basic-pitch), drum and beat grid refinement, multi-voice left-hand textures.
License
MIT. The Demucs weights are MIT and remain under their own license; they are downloaded, not redistributed here.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Read-only sheet music discovery and practice tools, with browser-local recognition guidance.
ScoreStarling is an all-in-one AI sheet music assistant. Ask for anything to do with sheet music: transcribe a song from audio, video or a link, read a PDF or photo, add chords, change the key, make it easier, turn it into guitar TAB or jianpu, or arrange it for another instrument. Every change lands on a real score you can hear, fix and download (PDF, MIDI, MusicXML, guitar TAB, jianpu, audio). Hosted remote server with OAuth sign-in. Free accounts get monthly credits and free previews; prices are at scorestarling.com/pricing. Setup: https://scorestarling.com/mcp
Transcribe with speaker labels, split stems, remove noise, separate speakers, convert audio to MIDI.
Find AI-transcribed sheet music, MIDI and stems for songs. /mcp/public needs no sign-in.
Related MCP Servers
- AlicenseAqualityBmaintenanceAI-powered music notation server that lets you create and edit scores using natural language, integrating with MuseScore for live manipulation.2399 PyPI32MIT
- AlicenseAqualityDmaintenanceEnables AI-driven MIDI composition with chord name support, interactive piano-roll preview, and multiple deployment modes.259MIT
- AlicenseNot gradedqualityBmaintenanceAI-assisted sheet music transcription and notation workflow via Agent and MCP.1Apache 2.0
- AlicenseBqualityBmaintenanceTurns lyrics plus a chord progression into a .ust file for UTAU/OpenUtau (one note per syllable, pitched to the chords) together with a same-length backing track as .mid and .wav. Also previews syllable splits, renders backing from chords alone, and lists available instruments, styles, lyric modes and chord qualities.25MIT