mcp-qobuz: Instructions file for Claude Code

CLAUDE.md

mcp-qobuz CLAUDE.md is an instructions file for Claude Code from kud/mcp-qobuz. It costs 464 tokens per session, scanned A, original, MIT.

A set of Claude Code instructions for working on mcp-qobuz, a server that connects coding agents to Qobuz music services. It documents the API, project structure, authentication, and a Mac-only now-playing feature.

In plain words
What is it for?
Use it when developing or maintaining mcp-qobuz, especially its API client, authentication paths, related Qobuz integrations, or now-playing support.
Why use it?
It gives an agent the project-specific rules and constraints needed to make changes safely, including how credentials work and which features only run on the same Mac as the Qobuz app.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is kud/mcp-qobuz's own configuration. It tells Claude Code how to work on mcp-qobuz 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 mcp-qobuz configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/kud/Projects/qobuz-cli.

Reuse

Borrowing it

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

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 mcp-qobuz CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kud/mcp-qobuz/claude-md.svg)](https://agentmods.dev/instructions/kud/mcp-qobuz/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kud/mcp-qobuz/claude-md"><img src="https://agentmods.dev/badge/instructions/kud/mcp-qobuz/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 464 This file is loaded in full into every session.
When invoked 464 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 $0.00464 $0.00464
Opus 5 $0.00232 $0.00232
Sonnet 5 $0.00093 $0.00093
Haiku 4.5 $0.00046 $0.00046

Measured 7d ago against content hash 2b1d5d139258, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mcp-qobuz 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 7d 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.

CLAUDE.md · 39 lines

What it actually says

mcp-qobuz

API Reference

Official API docs: https://www.qobuz.com/api.json/0.2 (unofficial — Qobuz has no public docs)

Core client: @kud/qobuz v0.5.5 — see /Users/kud/Projects/qobuz-cli and /Users/kud/Projects/raycast-extensions/extensions/qobuz for sibling surfaces using the same client.

Architecture

This server is one of six surfaces in the @kud/qobuz ecosystem:

  • @kud/qobuz — core client library (auth, API transport, types)
  • qobuz-cli — terminal surface
  • raycast-extensions/qobuz — Raycast surface
  • mcp-qobuz — MCP surface (this repo)

Auth

Two auth paths (both supported simultaneously):

  1. Keychain (createKeychainStore()) — for local Mac use, shares credentials with the CLI and Raycast extension via the "qobuz"/"default" keychain entry.
  2. Env vars (QOBUZ_TOKEN + QOBUZ_APP_ID) — for headless/remote use where macOS Keychain is unavailable.

Env vars take precedence over Keychain when present.

now-playing macOS constraint

client.nowPlaying() reads ~/Library/Application Support/Qobuz/player-0.json written by the Qobuz desktop app. This only works when the MCP server and Qobuz desktop app run on the same Mac. Return a graceful error on any other platform or when the file is absent.

The convert-link tool (Spotify/YouTube Music ↔ Qobuz via ISRC) is intentionally absent. The resolve logic is currently duplicated in:

  • /Users/kud/Projects/qobuz-cli/src/resolve.ts
  • /Users/kud/Projects/raycast-extensions/extensions/qobuz/src/lib/resolve.ts

The plan is to extract a shared @kud/song-match package first, then add convert-link here as a consumer of that shared lib. Do NOT copy resolve.ts into this repo.

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. 7d ago First seen · 39 lines · 464 tokens per session scan A 2b1d5d139258

Subscribe to this mod's changes

mcp-qobuz CLAUDE.md is an instructions file published in the GitHub repository kud/mcp-qobuz (0 stars, last pushed 27d ago), licensed MIT. It adds 464 tokens to every session, about $0.0023 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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens