Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ghchen99/mcp-musescore --skill mcp-musescoregit clone --depth 1 https://github.com/ghchen99/mcp-musescoreWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ghchen99/mcp-musescore/mcp-musescore)<a href="https://agentmods.dev/skills/ghchen99/mcp-musescore/mcp-musescore"><img src="https://agentmods.dev/badge/skills/ghchen99/mcp-musescore/mcp-musescore/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ghchen99/mcp-musescore/mcp-musescore"><img src="https://agentmods.dev/badge/skills/ghchen99/mcp-musescore/mcp-musescore.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00040 | $0.00927 |
| Opus 5 | $0.00020 | $0.00464 |
| Sonnet 5 | $0.00008 | $0.00185 |
| Haiku 4.5 | $0.00004 | $0.00093 |
Grade A, and why
mcp-musescore scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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 mcp 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.qmlplugin 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.pyover stdio. Usescripts/start-mcp-musescore.shorscripts/start-mcp-musescore.ps1for a manual launch; setMCP_MUSESCORE_DIRwhen the repository is not in~/Downloads/mcp-musescore. - Run
scripts/check-mcp-musescore.shor 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.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 253 B
- references/architecture.md 2.9 KB
- references/client-configuration.md 1.9 KB
- references/runtime.md 1.3 KB
- references/tools.md 5.4 KB
- scripts/check-mcp-musescore.ps1 790 B runs code
- scripts/check-mcp-musescore.sh 617 B runs code
- scripts/probe-musescore-bridge.py 918 B runs code
- scripts/start-mcp-musescore.ps1 818 B runs code
- scripts/start-mcp-musescore.sh 648 B runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 60 lines · 40 tokens per session scan A 02d2352cf521
mcp-musescore is a skill published in the GitHub repository ghchen99/mcp-musescore (86 stars, last pushed 5d ago), licensed MIT. It adds 40 tokens to every session and 927 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other skills, from other repositories
blender-expert
Expert Blender 3D modeling, animation, rendering, and pipeline automation. Use for any Blender-related task from simple primitives to complex procedural workflows.
autonomous-modeling
Use this skill to autonomously design and model complex 3D objects in Blender. Perfect for generating chassis, robots, and environment props from natural language.
pipeline-automation
Automate 3D asset pipelines, including batch optimization, material baking, and exports for platforms like Unity and VRChat.
bili-content-analysis
Deep analysis and tracking of Bilibili creators, videos, dynamics, and articles with BiliStalker MCP tools. Use when users ask for transcript interpretation, timeline reconstruction, theme extraction, behavior analysis, recent shift tracking, or discussion grounded in fetched Bilibili source material.
jellyfin-media-playback
Stream and control Jellyfin playback and browse music via the jellyfin-mcp MCP server — list artists, albums, and music genres, resolve audio/video streams, manage playlists, and drive playstate (play, mark played, report progress) with the domain-typed jellyfinmedia tool. Use when the agent must start or control…
midasheng-gen
Unified audio scene generation - speech, music, SFX, and ambience in one 16 kHz mix from structured text captions.