New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

MCP Musescore

by ghchen99 in ghchen99/mcp-musescore

Use the ghchen99/mcp-musescore MCP server to inspect, navigate, compose, and edit an open MuseScore score through its QML WebSocket plugin.

MITAuto-check passedAgent Workflows

Install MCP Musescore

skills CLI
$ npx skills add ghchen99/mcp-musescore --skill mcp-musescore -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ghchen99/mcp-musescore mcp-musescore --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ghchen99/mcp-musescore.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/mcp-musescore .claude/skills/mcp-musescore && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
mcp-musescore
GitHub stars
109
Token cost
~1.1k tokens
SKILL.md length
550 words
Files
11 (incl. scripts, references)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Use the ghchen99/mcp-musescore MCP server to inspect, navigate, compose, and edit an open MuseScore score through its QML WebSocket plugin.

  • Works in 6 steps: Call ping_musescore to verify the bridge. → Call get_score before editing so the… → Use navigation and selection tools to… → …
  • Tasks that involve MCP servers
  • SKILL.md covers Read the right detail, Routing rule, Preconditions and startup and Operating sequence, plus 3 more sections
  • Runs PowerShell, Shell and Python scripts from its folder

What it does

MCP Musescore is an agent skill from ghchen99/mcp-musescore. Use the ghchen99/mcp-musescore MCP server to inspect, navigate, compose, and edit an open MuseScore score through its QML WebSocket plugin.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/architecture.md` and `references/client-configuration.md`).

It sits in Agent Workflows, covering MCP servers and Realtime and WebSockets. It works with Model Context Protocol. The repository describes itself as: A Model Context Protocol (MCP) server that provides programmatic control over MuseScore! The licence is MIT.

When your agent uses it

  • Tasks that involve MCP servers
  • Tasks that involve Realtime and WebSockets

Example prompts

  • “/mcp-musescore”

Requirements

  • Python 3
  • A Bash shell
  • PowerShell

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Call ping_musescore to verify the bridge.
  2. Call get_score before editing so the current title, measures, staves, and score state are known.
  3. Use navigation and selection tools to place the cursor precisely.
  4. Use a direct mutation for one or two deliberate edits; use processSequence for a known batch.
  5. Call get_score or a navigation tool after each mutation batch and report what was verified.
  6. Saving or exporting .mscz, PDF, or audio remains a MuseScore UI action unless another configured tool provides it.

What it can do on your machine

Read from SKILL.md and the folder at commit cab6a74. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 5 files in scripts/ (PowerShell, Shell and Python), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

MCP Musescore loads about 1.1k tokens when it runs, and up to ~4k if it reads all its reference files. Until then it costs about 38 tokens; SKILL.md has 550 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~38
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from ghchen99/mcp-musescore at commit cab6a74, republished under its MIT licence (© ghchen99). 550 words, ~1,071 tokens.

Download SKILL.mdSave it as .claude/skills/mcp-musescore/SKILL.md (or your agent's skills folder). This skill also uses 10 other files; get the full folder from GitHub.
name
mcp-musescore
description
Use the ghchen99/mcp-musescore MCP server to inspect, navigate, compose, and edit an open MuseScore score through its QML WebSocket plugin.
metadata.short-description
Control an open MuseScore score

MuseScore MCP

Use this skill when a user asks to inspect, compose, edit, navigate, or analyze a score in MuseScore through the configured mcp-musescore server.

Read the right detail

  • Read references/tools.md before choosing a tool or constructing a batch sequence. It is the source of truth for the 26 public MCP tools, parameters, defaults, and upstream README discrepancies.
  • Read references/architecture.md when diagnosing connection, plugin, port, response-envelope, or MuseScore-version problems.
  • Read references/client-configuration.md when a client needs a stdio configuration.
  • Read references/runtime.md when installing, selecting a Python runtime, or using the repository's CLI helpers.

Routing rule

Prefer a purpose-built CLI command when it is actually available in the current environment for the requested operation. If no such CLI command is available, use the public MCP tools documented in references/tools.md. Never invent a MuseScore CLI command. The repository's fastmcp dev command is an MCP inspector/development helper; it is not a replacement for the live MuseScore editing tools.

Preconditions and startup

  • MuseScore Studio must be open with a score loaded.
  • The musescore-mcp-websocket.qml plugin must be enabled and running from MuseScore's Plugins menu.
  • The plugin must listen on ws://localhost:8765.
  • The MCP client must launch the repository's server.py over stdio. Use scripts/start-mcp-musescore.sh or scripts/start-mcp-musescore.ps1 for a manual launch; set MCP_MUSESCORE_DIR when the repository is not in ~/Downloads/mcp-musescore.
  • Run scripts/check-mcp-musescore.sh or its PowerShell equivalent when a deterministic bridge probe is needed.

If a tool reports Not connected to MuseScore, do not retry mutations blindly: start or reload the MuseScore plugin, call ping_musescore, and only then continue.

Operating sequence

  1. Call ping_musescore to verify the bridge.
  2. Call get_score before editing so the current title, measures, staves, and score state are known.
  3. Use navigation and selection tools to place the cursor precisely.
  4. Use a direct mutation for one or two deliberate edits; use processSequence for a known batch.
  5. Call get_score or a navigation tool after each mutation batch and report what was verified.
  6. Saving or exporting .mscz, PDF, or audio remains a MuseScore UI action unless another configured tool provides it.
Show full SKILL.md (213 more words)Show less

Guardrails

  • Do not claim that an edit succeeded without a follow-up read from MuseScore.
  • Preserve the user's score, cursor, and selection unless the requested operation changes them.
  • Confirm pitch, duration, staff, voice, measure, and cursor-advance intent before destructive or cumulative edits.
  • Use undo when a just-made mutation is wrong and the score state is still safe to reverse.
  • Treat the JSON returned by the bridge as authoritative. The upstream README contains historical names such as add_lyrics_to_current_note and set_title that are not currently registered public MCP tools; do not call them unless the repository exposes them in a future version.
  • processSequence is camelCase because that is the registered Python tool name. Its inner action values are also camelCase QML actions; see the reference for the supported set.

Portability

This folder is a normal SKILL.md skill for Claude Code and compatible loaders. Codex also uses agents/openai.yaml for UI metadata. The skill does not embed secrets, API keys, or machine-specific absolute paths.

Guardrails

  • Treat the score returned by get_score as the source of truth; do not claim an edit succeeded without a follow-up read.
  • Preserve the user's existing score and selection unless the requested operation requires changing them.
  • Saving or exporting .mscz, PDF, or audio remains a MuseScore application action unless another configured tool is available.

© ghchen99, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 10 other files (scripts, references) in skills/mcp-musescore of ghchen99/mcp-musescore.

  • SKILL.md
  • agents/openai.yaml
  • references/architecture.md
  • references/client-configuration.md
  • references/runtime.md
  • references/tools.md
  • scripts/check-mcp-musescore.ps1
  • scripts/check-mcp-musescore.sh
  • scripts/probe-musescore-bridge.py
  • scripts/start-mcp-musescore.ps1
  • scripts/start-mcp-musescore.sh

Open the folder on GitHubat commit cab6a74

Compare with similar skills

MCP Musescore next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

MCP Musescore compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
MCP Musescore this skillghchen99/mcp-musescore109—~1.1kAutomated safety check: PassMIT
Building MCP Serversaiskillstore/marketplace430—~2.2kAutomated safety check: NotesNone
Openai Docsaafqaq/codex-lb-enhanced1032 repos~861Automated safety check: PassApache-2.0
Agents SDKhodgef/apiker1273 repos~3kAutomated safety check: PassMIT
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k5 repos~1.2kAutomated safety check: PassMIT

Similar skills

  • Building MCP Servers

    aiskillstore/marketplace

    Expert at integrating Model Context Protocol (MCP) servers into Claude Code plugins.

    430 GitHub stars~2.2k tokensUpdated today
    Agent WorkflowsAuto-check: notes

  • Openai Docs

    aafqaq/codex-lb-enhanced

    A skill your agent uses when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations (for example: Codex, Responses API, Chat Completions…

    103 GitHub starsUsed in 2 repos~861 tokens
    DevOps & CloudAuto-check passed

  • Agents SDK

    hodgef/apiker

    Build AI agents on Cloudflare Workers using the Agents SDK. An agent skill from hodgef/apiker.

    127 GitHub starsUsed in 3 repos~3k tokens
    Backend & APIsAuto-check passed

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed

  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 5 repos~1.2k tokens
    Agent WorkflowsAuto-check passed

  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    38k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed

Works with

Categories

Questions about MCP Musescore

What does MCP Musescore do?

Use the ghchen99/mcp-musescore MCP server to inspect, navigate, compose, and edit an open MuseScore score through its QML WebSocket plugin. MCP Musescore is an agent skill from ghchen99/mcp-musescore. Use the ghchen99/mcp-musescore MCP server to inspect, navigate, compose, and edit an open MuseScore score through its QML WebSocket plugin.

When should I use MCP Musescore?

MCP Musescore fits situations like: tasks that involve MCP servers; tasks that involve Realtime and WebSockets.

How do I install MCP Musescore in Claude Code?

Run `npx skills add ghchen99/mcp-musescore --skill mcp-musescore -a claude-code`. Or copy the skill folder (skills/mcp-musescore in ghchen99/mcp-musescore) into .claude/skills/mcp-musescore in your project. Claude Code loads it when a task matches its description.

How do I install MCP Musescore in Codex?

Run `npx skills add ghchen99/mcp-musescore --skill mcp-musescore -a codex`. Or copy the skill folder (skills/mcp-musescore in ghchen99/mcp-musescore) into .agents/skills/mcp-musescore in your project. Codex loads it when a task matches its description.

Can I use MCP Musescore in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ghchen99/mcp-musescore --skill mcp-musescore -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mcp-musescore, .gemini/skills/mcp-musescore, .github/skills/mcp-musescore and .opencode/skills/mcp-musescore in your project.

What does MCP Musescore need to run?

Going by SKILL.md and its folder, MCP Musescore needs PowerShell, a shell and Python for the scripts in its folder. Our summary lists: Python 3; A Bash shell; PowerShell.

Does MCP Musescore access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is MCP Musescore safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does MCP Musescore use?

MCP Musescore is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does MCP Musescore use?

About 1.1k tokens (SKILL.md is roughly 4.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3k tokens, read only when the agent opens those files.

What are the alternatives to MCP Musescore?

Skills that share tags, products or a category with MCP Musescore: Building MCP Servers (aiskillstore/marketplace, 430 stars), Openai Docs (aafqaq/codex-lb-enhanced, 103 stars), Agents SDK (hodgef/apiker, 127 stars) and MCP Server Builder (anthropics/skills, 180k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains MCP Musescore?

ghchen99 (a GitHub user) maintains it in ghchen99/mcp-musescore, which has 109 GitHub stars. The repository was last updated on October 7, 2026.

Source: ghchen99/mcp-musescore on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.