Dorico Maestro
The server lets an AI assistant remote-control Steinberg Dorico via MCP (note input, playback, transposition, mode switching) and run offline music-analysis tools.
Connect to Dorico and read its live status (
connect_to_dorico,get_status)Add notes, rests, and chords at the caret with durations, accidentals, and as-chord stacking (
add_notes,add_rest)Transpose the current selection up/down, chromatic or by octave (
transpose)Switch between Write/Engrave/Play/Print/Setup modes (
switch_mode)Control playback (play/stop, choose start location) and save the project (
playback,save)Move the viewport to start/end of score (
navigate; bar-jump is unsupported)Run any catalogued Dorico command via a generic escape hatch (
run_command), including destructive ones with confirmationDiscover the full command catalog, its parameters, and verification status via the
dorico://commandsresourceOffline theory tools are available (not in the schema but described in the README): analyze harmony, check voice leading, suggest next chord, instrument range, counterpoint checks, and full-score writing via a
ScoreSpec
Provides tools to control Steinberg Dorico through its Remote Control API, enabling note input, rests, transposition, mode switching, playback control, and score edits in an open Dorico project.
Click on "Install 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., "@Dorico MaestroAdd a C major chord in the piano part"
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.
Dorico Maestro
An AI composition partner that remote-controls Steinberg Dorico through the Model Context Protocol (MCP).
Dorico Maestro turns Dorico into a shared canvas between a composer and an AI assistant. You discuss a musical idea in plain language; the assistant writes it into your open Dorico score, plays it back, and the two of you refine it together — bar by bar.
Status: experimental (v0.1), but broadly exercised. 176 of 344 catalogued commands are verified live against Dorico 6 (returned
kOK), 3 are known-broken, and the rest are not yet exercised — many are recognised by Dorico but need a specific context, or open dialogs that can't be auto-tested. Every command carries an honest status (verified/broken/untested) insrc/dorico_maestro/commands.yaml, also served by thedorico://commandsresource.
How it works
You ⇄ Claude (LLM) ⇄ Dorico Maestro (MCP server) ⇄ Dorico (Remote Control · WebSocket 127.0.0.1:4560)
│
└─ music21 ⇄ MusicXML (full-score generation & reading)Data-driven core — every Dorico command is described as data in
commands.yaml; one generic builder/executor sends them, so behaviour is consistent and adding a command is a data change, not new code.Small, honest MCP surface — a handful of musical tools (
add_notes,transpose,playback, …), a genericrun_command, and adorico://commandsresource to discover the whole catalog.kOKfrom Dorico means accepted, not effective — results say which.Full-score awareness — Dorico's API can only read the current selection, so whole-piece understanding uses MusicXML + music21.
A "music brain" — a typed
ScoreSpecthe assistant fills in, plus offline theory (key detection, Roman-numeral analysis, voice-leading & parallel checks, instrument ranges, species counterpoint). It writes a whole score into Dorico through the guaranteed caret path (verified commands only, zero manual steps) or, for richer notation, exports/imports MusicXML.
Related MCP server: MuseScore MCP Server
Requirements
Steinberg Dorico (Remote Control API; introduced in Dorico 4, tested on Dorico 6), with Remote Control enabled.
Python 3.11+.
An MCP client (Claude Desktop / Claude Code).
Install
git clone git@github.com:romanstark/dorico-maestro.git
cd dorico-maestro
python -m venv .venv
.venv\Scripts\activate # Windows (use source .venv/bin/activate on macOS/Linux)
pip install -e ".[dev]"
pytest # optional: 243 tests, no Dorico neededEnable Dorico's Remote Control
In Dorico, turn on the Remote Control API (it listens on
127.0.0.1:4560).The first time Dorico Maestro connects, Dorico asks you to allow the connection — accept it. On the very first connect you may be prompted more than once (allow it twice); accept each time. A session token is then stored and reused, so later runs connect without a prompt.
Register with your MCP client
Add to your client's mcpServers config (adjust the path to your checkout):
{
"mcpServers": {
"dorico-maestro": {
"command": "/absolute/path/to/dorico-maestro/.venv/Scripts/python.exe",
"args": ["-m", "dorico_maestro.server"]
}
}
}Restart the client, open a score in Dorico, then say "connect to Dorico".
Usage
Talk to the assistant naturally; it drives these tools:
connect_to_dorico,get_status— connect and read Dorico's live state.add_notes(["C4","E4","G4"], duration="quarter")— enter notes at the caret (accidentals like"F#5"/"Bb3"supported), then leaves note input cleanly.add_rest,transpose,switch_mode,playback,save.write_score(score)— write a wholeScoreSpec(JSON) into Dorico via the guaranteed caret path (ormethod="musicxml");render_to_dorico(score, dry_run=True)previews the exact command plan without sending.export_musicxml/import_musicxml— full-fidelity MusicXML out, best-effort in.analyze_harmony,check_voice_leading,suggest_next_chord,instrument_range,check_counterpoint— offline theory, no Dorico needed.run_command(command_id, params)— the escape hatch for any catalogued command.Resource
dorico://commands(anddorico://commands/{category|status}) — discover the full command set and its verification status.
What works / current limits
Verified live (176 commands): connect + status; note input (pitch/duration/accidental/rest/tie/dot/chords); selection & event navigation; all zoom/viewport; playback transport; all five window modes; transposition (
NoteEdit.*); and much ofEventEdit.*.Whole-score composition & theory (offline + caret): a typed
ScoreSpecdrives full-score writing through the verified caret path (multi-staff piano is proven live) and a battery of offline theory tools; multi-instrument caret entry is flagged experimental until verified live.Selection-only reads: there is no "read bar N" — the API reads only the current selection; whole-score reading will go via MusicXML export + music21.
Popover-only actions not yet supported: time/key signatures and dynamics are entered via a Dorico popover whose value the API can't fill, so those tools report the limitation instead of silently doing nothing.
kOK≠ effect: tools verify where they can and say so; otherwise confirm in the score.
Contributing
Contributions are very welcome — via GitHub Issues and Pull Requests. CI runs the tests and linter on every PR. Because the project is dual-licensed (see below), contributors sign a lightweight CLA. Start with CONTRIBUTING.md.
Good first tasks: live-verify untested commands (flip their status in
commands.yaml), enrich command params from Dorico's application.log, or help
build the MusicXML round-trip.
License
AGPL-3.0-or-later — see LICENSE. The software is free and open; if you deploy a modified version, you must share your source under the same license.
Commercial licensing: if you want to use Dorico Maestro in a proprietary or closed-source product (AGPL terms don't fit), a separate commercial license is available — contact Roman Stark (mail@romanstark.de).
Third-party notices: see THIRD-PARTY.md — Dorico Maestro builds on music21 (BSD-3-Clause) and the royalty-free MusicXML format; neither restricts this project's licensing.
Documentation
docs/architecture.md — how the data-driven design fits together
docs/protocol.md — the reverse-engineered Dorico Remote Control protocol
docs/dorico_command_catalog.md — all ~340 command IDs
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
AI image, video, voice and music generation over MCP, routed to Veo 3.1, Seedance 2.0 and more.
Choir management for AI assistants: events, RSVP, announcements and sheet music of your choir.
Generate AI music via the Lacuna Music API from MCP clients like Claude Desktop & Code.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceConnects Ableton Live to AI assistants through Model Context Protocol (MCP), enabling natural language control of music production tasks like track creation, MIDI editing, instrument loading, and playback control.15MIT
- AlicenseNot gradedqualityCmaintenanceA Model Context Protocol server that provides programmatic control over MuseScore through a WebSocket-based plugin system, allowing AI assistants to compose music, add lyrics, navigate scores, and control MuseScore directly.82MIT
- AlicenseAqualityDmaintenanceAI-powered music notation server that lets you create and edit scores using natural language, integrating with MuseScore for live manipulation.1820MIT
- AlicenseBqualityDmaintenanceAn MCP server that enables natural language control of Steinberg Dorico music notation software through Claude Desktop or ChatGPT, offering tools for score creation, note input, notation, harmony analysis, and orchestration.5411MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/romanstark/dorico-maestro'
If you have feedback or need assistance with the MCP directory API, please join our Discord server