What is mcp-score AGENTS.md?

Documentation and instructions for mcp-score, a project that generates and edits musical scores. It describes a standalone score-generation skill and an MCP server that connects to MuseScore, Dorico, or Sibelius.

Use it when developing, running, or modifying mcp-score, including score generation, live score analysis, and edits such as changing keys, tempo, chords, or transposition.

It explains how the two parts fit together and gives developers the project structure and conventions needed to work on it.

How tskovlund/mcp-score configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to tskovlund/mcp-score. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/tskovlund/mcp-score/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/tskovlund/mcp-score

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/tskovlund/mcp-score/agents-md/github.svg)](https://agentmods.dev/instructions/tskovlund/mcp-score/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/tskovlund/mcp-score/agents-md"><img src="https://agentmods.dev/badge/instructions/tskovlund/mcp-score/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/tskovlund/mcp-score/agents-md"><img src="https://agentmods.dev/badge/instructions/tskovlund/mcp-score/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,755 This file is loaded in full into every session.

When invoked 1,755 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01755	$0.01755
Opus 5.5	$0.00702	$0.00702
Sonnet 5.5	$0.00351	$0.00351
Haiku 4.5	$0.00176	$0.00176

Measured 1mo ago against content hash 2649e5009b26, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-score AGENTS.md 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 1mo 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.

AGENTS.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mcp-score

AI-driven music score generation and manipulation, for any MCP client. Three jobs:

Score generation — the assistant writes a music21 Python script that exports MusicXML. In Claude Code the bundled score-generate skill (.claude/skills/score-generate/) drives this without MCP. In other clients the generate_score tool runs the script and score_generation_guide (also the score-generate MCP prompt) serves the same instructions.
Live score manipulation via MCP server — reads from and writes to a running MuseScore Studio 4.4.2+ (or experimentally Dorico) via WebSocket bridge.
Rendering — render_score exports PDF, PNG, MIDI, audio or MusicXML through the MuseScore command line.

Follow the code standards in CONVENTIONS.md.

Architecture

src/mcp_score/
  cli.py              CLI entry point (serve, run, install, install-skill, install-plugin)
  server.py           MCP server entry point: create_server() registers every tool module
  context.py          AppState and ScoreContext: what the server hands every tool
  guide.py            The score-generate skill assembled into one document for MCP clients
  resources.py        Locate bundled files (skill directory, plugin directory)
  tools/
    base.py           Shared tool plumbing: ToolError, score_tool, bridge and measure guards
    connection.py     Connect/disconnect MuseScore & Dorico, ping, score info
    analysis.py       Read passages and measures from live score
    manipulation.py   Modify live score (notes, rehearsal marks, dynamics, chords, barlines, keys, time, tempo, measures, transpose, undo)
    generate.py       Run music21 scripts and serve the score-generate guide (any MCP client)
    render.py         Export score files through the MuseScore command line
  bridge/
    base.py           ScoreBridge abstract interface and BridgeError
    results.py        The result models every operation returns (published as tool output schemas)
    websocket.py      WebSocketTransport and WebSocketBridge (connection lifecycle, reconnect)
    remote_control.py Remote Control protocol layer (used by Dorico)
    musescore.py      MuseScore plugin protocol on WebSocketBridge
    dorico.py         Dorico defaults (thin subclass of RemoteControlBridge, experimental)
    registry.py       BridgeRegistry: the bridges and which one is active
  musescore/
    paths.py          Where MuseScore keeps user files (plugins directory)
    executable.py     Where MuseScore's executable is (env var, PATH, platform defaults)
    headless.py       Headless rendering through the MuseScore command line
    plugin/           MuseScore plugin: mcp-score-bridge.qml (server, dispatch) and its JS modules

.claude/skills/
  score-generate/     Claude Code skill for score generation via music21
    SKILL.md
    references/       instruments.md, template.py

scripts/
  musescore_harness.py  Installs and drives a real MuseScore for integration tests

tests/                pytest tests, grouped by concern, offline
tests/integration/    Tests against a real MuseScore (opt-in, MCP_SCORE_INTEGRATION=1)
docs/                 Diataxis-structured documentation

Read the full file on GitHub · 138 lines

Changes

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.

1mo ago Changed · -2 lines · -115 tokens per session 2649e5009b26
1mo ago Changed · +22 lines · +708 tokens per session 74e19bf605e6
2mo ago Changed 25f39606c1df
2mo ago First seen · 118 lines · 1,162 tokens per session scan A e72e88620457

Subscribe to this mod's changes

mcp-score AGENTS.md is an instructions file published in the GitHub repository tskovlund/mcp-score (32 stars, last pushed 6d ago), licensed MIT. It adds 1,755 tokens to every session, about $0.0070 per session on Opus 5.5. 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 2026-08-30.

Creative and media ai claude mcp mcp-server musescore music

mcp-score AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-score AGENTS.mdtskovlund/mcp-score	Instructions file	32	6d ago	MIT	A	1,755	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

mcp-score: Instructions file for Codex