Borrowing it
Nothing to install: this file belongs to crlian/mcp-pyatv. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/crlian/mcp-pyatv/main/CLAUDE.mdgit clone --depth 1 https://github.com/crlian/mcp-pyatvWrote 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/instructions/crlian/mcp-pyatv/claude-md)<a href="https://agentmods.dev/instructions/crlian/mcp-pyatv/claude-md"><img src="https://agentmods.dev/badge/instructions/crlian/mcp-pyatv/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.
<a href="https://agentmods.dev/instructions/crlian/mcp-pyatv/claude-md"><img src="https://agentmods.dev/badge/instructions/crlian/mcp-pyatv/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.01146 | $0.01146 |
| Opus 5 | $0.00573 | $0.00573 |
| Sonnet 5 | $0.00229 | $0.00229 |
| Haiku 4.5 | $0.00115 | $0.00115 |
Grade A, and why
mcp-pyatv 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 9d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
mcp-pyatv is an MCP (Model Context Protocol) server that bridges Claude and other MCP clients to Apple TV, HomePod, and AirPlay devices on a local network. It wraps the pyatv Python library and exposes device control as 32 MCP tools via FastMCP 2.0+.
Build & Run
# Install from source (editable)
pip install -e .
# Run the server
mcp-pyatv
# or
python -m mcp_pyatv.server
# Run via uvx (no install)
uvx mcp-pyatv
Build system is hatchling (configured in pyproject.toml). No linter/formatter configuration exists. No automated tests exist yet (tests/ is empty).
Python: 3.11, 3.12, 3.13 supported. 3.14 is not supported (asyncio issues in upstream pyatv).
Architecture
Server Lifecycle (server.py)
FastMCP server with lazy initialization: storage and connections are created on first tool call (not at startup) to avoid timeouts during MCP handshake. The lifespan context exposes two lazy getters:
ctx.lifespan_context["get_connections"]()→ConnectionManagerctx.lifespan_context["get_storage"]()→FileStorage
Connection Management (connection.py)
ConnectionManager wraps pyatv's scan/connect/pair APIs and maintains two caches:
_connections: device identifier → connected AppleTV instance_configs: device identifier → device config metadata
Device resolution (conn.get(device)): if device=None, auto-selects when exactly 1 device exists. Otherwise matches by name (case-insensitive) or identifier. Scans the network if device not in cache.
Storage (storage.py)
Wraps pyatv.storage.FileStorage for credential persistence at ~/.pyatv.conf (configurable via MCP_PYATV_STORAGE_PATH env var). This file is shared with the atvremote CLI tool.
Tools (tools/)
9 modules, 32 tools total:
| Module | Tools | Notes |
|---|---|---|
discovery.py |
scan_devices, device_info |
Network scanning |
pairing.py |
start_pairing, finish_pairing |
Stateful pairing flow with global state |
remote.py |
13 tools (play, pause, navigate, seek, etc.) | Largest module |
power.py |
turn_on, turn_off, power_state |
|
audio.py |
get_volume, set_volume, volume_up, volume_down |
|
apps.py |
list_apps, launch_app |
Match by name or bundle_id |
keyboard.py |
set_text, get_text, clear_text |
|
now_playing.py |
now_playing, get_artwork |
Artwork is base64-encoded |
stream.py |
play_url, stream_file |
AirPlay streaming |
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.
- 9d ago First seen · 109 lines · 1,146 tokens per session scan A 52f78ede2fbc
mcp-pyatv CLAUDE.md is an instructions file published in the GitHub repository crlian/mcp-pyatv (1 stars, last pushed 5mo ago), licensed MIT. It adds 1,146 tokens to every session, about $0.0057 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.
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.
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.
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).
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).
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.
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.