What is hass-mcp CLAUDE.md?

Project instructions for a Home Assistant integration that adds an AI-tool interface to Home Assistant, a system for controlling smart-home devices. They describe its commands, web connection, authentication, structure, and tests.

Use them when adding or changing tools, maintaining the integration, checking its web requests, running tests, or installing it in Home Assistant.

They give developers the rules for extending the integration safely and consistently while keeping its connection compatible with Home Assistant security.

How czechbol/hass-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to czechbol/hass-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/czechbol/hass-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/czechbol/hass-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/czechbol/hass-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/czechbol/hass-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/czechbol/hass-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/czechbol/hass-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.

Your own site · 80×15

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

Per session 1,322 This file is loaded in full into every session.

When invoked 1,322 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	$0.01322	$0.01322
Opus 5.5	$0.00529	$0.00529
Sonnet 5.5	$0.00264	$0.00264
Haiku 4.5	$0.00132	$0.00132

Measured 2mo ago against content hash c35e2f2223d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hass-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 2mo 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 · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 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 when working with code in this repository.

What this is

HACS-installable Home Assistant custom integration that mounts a Model Context Protocol (MCP) server inside HA at POST /api/hass_mcp. Exposes ~32 generic meta-tools (ha_*) covering the full HA admin surface. Stateless Streamable HTTP transport, JSON-RPC body, reuses HA bearer auth.

Single Python package: custom_components/hass_mcp/.

Commands

ruff check .             # lint
ruff format --check .    # format check (use `ruff format .` to apply)
pytest -v                # full test suite
pytest tests/test_protocol.py::test_xyz -v   # single test
pip install -r requirements_test.txt         # install dev deps

CI runs hassfest, hacs/action, ruff, pytest on Python 3.13 — see .github/workflows/ci.yml. hassfest and hacs/action are Docker-based; don't bother running locally.

Dev install: symlink custom_components/hass_mcp into an HA config's custom_components/, restart HA, watch log for MCP endpoint registered.

Architecture

Request lifecycle: aiohttp POST → MCPView (http.py) → RateLimiter (sliding-window, keyed on last 32 chars of bearer) → protocol.dispatch (JSON-RPC: initialize, tools/list, tools/call, ping) → registry.TOOLS[name].handler(hass, **args).

Layout under custom_components/hass_mcp/:

__init__.py — integration setup, option propagation into hass.data.
http.py — HomeAssistantView, rate-limit gate, JSON encoder (_json_default handles MappingProxyType, datetime, Enum, set).
protocol.py — JSON-RPC routing + ToolError wrap-to-isError:true.
registry.py — @tool decorator, ToolDef, schema() helper, LIMIT_FIELD / OFFSET_FIELD / paginate().
rate_limit.py — per-key sliding-window limiter.
ws.py — in-process WebSocket dispatch (ws_call) for HA features with no Python API (helpers, backup, lovelace, HACS, system_log, auth). Builds a fake ActiveConnection with an admin user.
config_flow.py + strings.json + translations/ — UI option form.
tools/ — one file per tool group; tools/__init__.py imports each module which side-effect-registers handlers via @tool(...).

Read the full file on GitHub · 102 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.

2mo ago First seen · 102 lines · 1,322 tokens per session scan A c35e2f2223d9

Subscribe to this mod's changes

hass-mcp CLAUDE.md is an instructions file published in the GitHub repository czechbol/hass-mcp (2 stars, last pushed 16d ago), licensed MIT. It adds 1,322 tokens to every session, about $0.0053 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 2026-08-31.

Hardware and IoT hacs home-assistant mcp model-context-protocol

hass-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
hass-mcp CLAUDE.mdczechbol/hass-mcp	Instructions file	2	16d ago	MIT	A	1,322	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	144k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	281k	yesterday	MIT	A	4,335	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot

hass-mcp: Instructions file for Claude Code