synth-mcp
MCP server that synthesizes audio from MusicXML. Supports voice part selection (Soprano, Alto, Tenor, Bass) and tempo control.
What it does
Takes a MusicXML score, optionally filters to one or more voice parts, and renders a WAV audio file using FluidSynth. Useful for choir singers who want to practice a specific voice part.
Tools
| Tool | Description |
|---|---|
get_parts |
List all voice parts in a score — returns part name, ID, and measure count |
synthesize |
Render the score (or selected parts) to a WAV file, with optional tempo adjustment |
list_capabilities |
Return server metadata: backend version, soundfont status, FluidSynth availability |
Installation
cd synth-mcp
uv sync
System library required:
# Ubuntu / Debian
sudo apt install libfluidsynth-dev
# macOS
brew install fluid-synth
A soundfont (SF2) file is also required. Free options:
| Soundfont | Size | Notes |
|---|---|---|
| TimGM6mb | ~6 MB | Ships with Ubuntu (/usr/share/sounds/sf2/TimGM6mb.sf2) |
| MuseScore General | ~200 MB | Better quality; download from musescore.org |
| GeneralUser GS | ~30 MB | Download from schristiancollins.com |
Running
SYNTH_SOUNDFONT_PATH=/usr/share/sounds/sf2/TimGM6mb.sf2 uv run synth-mcp
Configuration
| Variable | Required | Description |
|---|---|---|
SYNTH_SOUNDFONT_PATH |
Yes | Path to an SF2 soundfont file |
Claude Desktop configuration
{
"mcpServers": {
"synth": {
"command": "uv",
"args": ["--directory", "/absolute/path/to/synth-mcp", "run", "synth-mcp"],
"env": {
"SYNTH_SOUNDFONT_PATH": "/absolute/path/to/soundfont.sf2"
}
}
}
}
Usage examples
// List parts in a score
{"tool": "get_parts", "arguments": {"musicxml": "<score-partwise>...</score-partwise>"}}
// Synthesize the full score
{
"tool": "synthesize",
"arguments": {
"musicxml": "<score-partwise>...</score-partwise>",
"output_path": "/tmp/full.wav"
}
}
// Synthesize Soprano part only at 80% tempo
{
"tool": "synthesize",
"arguments": {
"musicxml": "<score-partwise>...</score-partwise>",
"output_path": "/tmp/soprano.wav",
"part_ids": ["P1"],
"tempo_factor": 0.8
}
}
tempo_factor range: 0.25–4.0. Values below 1.0 slow down; above 1.0 speed up. Does not affect pitch.
Testing
# Unit tests (no soundfont required)
VIRTUAL_ENV= .venv/bin/pytest tests/ -v
# Integration tests (synthesizes real audio)
VIRTUAL_ENV= SYNTH_SOUNDFONT_PATH=/usr/share/sounds/sf2/TimGM6mb.sf2 \
.venv/bin/pytest tests/ -v -m integration
Dependencies
- music21 — score parsing and MIDI export
- pyfluidsynth — Python bindings for FluidSynth
- mcp — MCP protocol
Known limitations
- music21's MIDI export may drop some articulations and dynamics
- Audio output is always WAV; convert with
ffmpeg -i out.wav out.mp3if needed - Large scores (100+ measures) may take several seconds to synthesize
System requirements
- Python 3.11+
libfluidsynthshared library (libfluidsynth.so.3on Linux)- An SF2 soundfont file
1 maintainer
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
synth_mcp-0.1.2.tar.gz
(140.0 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
synth_mcp-0.1.2-py3-none-any.whl
(10.1 kB
view details)
File details
Details for the file synth_mcp-0.1.2.tar.gz.
File metadata
- Download URL: synth_mcp-0.1.2.tar.gz
- Upload date:
- Size: 140.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via:
twine/7.0.0 CPython/3.13.14
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e1431d94bdedcaae2d93599532d4da25e2d77e55e1ccb6cd9189f8cf80916a33
|
|
| MD5 |
b00cd00fa12b95fcdadb294db240db39
|
|
| BLAKE2b-256 |
35464386702e544b87258cac79c68fdd8a12852b589dbb8cbf5a3f3fdd3d72bc
|
Provenance
The following attestation bundles were made for synth_mcp-0.1.2.tar.gz:
Publisher:
publish.yml on raulkivi/music-assistant
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
synth_mcp-0.1.2.tar.gz -
Subject digest:
e1431d94bdedcaae2d93599532d4da25e2d77e55e1ccb6cd9189f8cf80916a33 - Sigstore transparency entry: 2481863475
- Sigstore integration time:
-
Permalink:
raulkivi/music-assistant@7ff9527a4037d29c77405611f71c19f607945c70 -
Branch / Tag:
refs/tags/synth-mcp/v0.1.2 - Owner: https://github.com/raulkivi
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
publish.yml@7ff9527a4037d29c77405611f71c19f607945c70 -
Trigger Event:
push
-
Statement type:
File details
Details for the file synth_mcp-0.1.2-py3-none-any.whl.
File metadata
- Download URL: synth_mcp-0.1.2-py3-none-any.whl
- Upload date:
- Size: 10.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via:
twine/7.0.0 CPython/3.13.14
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
7426b527985640388a4fd495eaab5a74b06aa8eab406d3c9180651b8643de6a2
|
|
| MD5 |
8da43655f4f28a9252b02a06fe01d869
|
|
| BLAKE2b-256 |
3e354ad986d7040b3993515373577c7c129704d1bb0ddd303ff28d3113569446
|
Provenance
The following attestation bundles were made for synth_mcp-0.1.2-py3-none-any.whl:
Publisher:
publish.yml on raulkivi/music-assistant
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
synth_mcp-0.1.2-py3-none-any.whl -
Subject digest:
7426b527985640388a4fd495eaab5a74b06aa8eab406d3c9180651b8643de6a2 - Sigstore transparency entry: 2481863531
- Sigstore integration time:
-
Permalink:
raulkivi/music-assistant@7ff9527a4037d29c77405611f71c19f607945c70 -
Branch / Tag:
refs/tags/synth-mcp/v0.1.2 - Owner: https://github.com/raulkivi
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
publish.yml@7ff9527a4037d29c77405611f71c19f607945c70 -
Trigger Event:
push
-
Statement type:
