grandorgue-mcp: Instructions file for Claude Code

CLAUDE.md

grandorgue-mcp CLAUDE.md is an instructions file for Claude Code from sandraschi/grandorgue-mcp. It costs 430 tokens per session, scanned A, original, MIT.

A project guide for GrandOrgue MCP, a server that lets an AI connect to the GrandOrgue pipe-organ simulator, MIDI devices, organ controls, sample sets, and a web console. It documents how the server starts, communicates, and is organized.

In plain words
What is it for?
Use it when developing or debugging the GrandOrgue MCP server, its web app, MIDI bridge, transports, or file-handling code.
Why use it?
It gives contributors the project’s entry points and coding rules so they can change the server without bypassing its safety and structure requirements.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code; mentions AGENTS.md.

This is sandraschi/grandorgue-mcp's own configuration. It tells Claude Code how to work on grandorgue-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything grandorgue-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sandraschi/grandorgue-mcp. 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/sandraschi/grandorgue-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/sandraschi/grandorgue-mcp

Made for: Claude Code.

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.

agentmods badge for grandorgue-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sandraschi/grandorgue-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/sandraschi/grandorgue-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sandraschi/grandorgue-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sandraschi/grandorgue-mcp/claude-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.

agentmods 80×15 button for grandorgue-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sandraschi/grandorgue-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sandraschi/grandorgue-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 430 This file is loaded in full into every session.
When invoked 430 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00430 $0.00430
Opus 5 $0.00215 $0.00215
Sonnet 5 $0.00086 $0.00086
Haiku 4.5 $0.00043 $0.00043

Measured today against content hash 7fd4c9db1cd5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

grandorgue-mcp CLAUDE.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 today.

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.

CLAUDE.md · 25 lines

What it actually says

grandorgue-mcp — Claude Code Guide

Overview

GrandOrgue pipe organ simulator MCP server — MIDI bridge, organ control, sample set management, modern web console

Entry Points

  • stdio (Claude Desktop / mcpb, default): uv run grandorgue-mcp
  • HTTP (webapp backend :11010, MCP at /mcp): MCP_TRANSPORT=http uv run grandorgue-mcp or just run
  • Full webapp (backend + Vite frontend :11011): just web / .\start.ps1

Standards

  • Flat FastMCP tools (30) with an operation-style portmanteau refactor planned for v0.3 — do NOT claim portmanteau compliance yet
  • Dual transport via MCP_TRANSPORT env: stdio (default) | http
  • Responses: structured dicts with success, message, domain-specific fields
  • Shared logic lives in plain helper functions; NEVER call an @mcp.tool()-decorated object directly (FunctionTool is not callable — use the _impl helpers)
  • Depot file names must go through _depot_path() (traversal-safe)
  • Blocking work (subprocess, rtmidi) goes through anyio.to_thread.run_sync
  • See mcp-central-docs for fleet-wide coding standards

Key Files

  • src/grandorgue_mcp/server.py — tools, REST, WS, transports (single canonical server; mcpb stages from here)
  • pyproject.toml — build config and entry points (fastmcp>=3.4.2,<4)
  • scripts/mcpb-pack.ps1 — mcpb bundle staging + pack (just mcpb; wraps fleet make-mcpb.ps1, fresh-stages src/)
  • README.md — full documentation; AGENTS.md — agent context
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.

  1. today Changed · +12 tokens per session 7fd4c9db1cd5
  2. 9d ago First seen · 25 lines · 418 tokens per session scan A 39fbc36294b5

Subscribe to this mod's changes

grandorgue-mcp CLAUDE.md is an instructions file published in the GitHub repository sandraschi/grandorgue-mcp (2 stars, last pushed yesterday), licensed MIT. It adds 430 tokens to every session, about $0.0022 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 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens