GitHub
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
作者による説明(英語の原文)
Home Assistant and ESPHome for coding agents: states, services, automations, dashboards, flashing.
この3つを1つのスコアにまとめることはしません。意見、測定、人気はそれぞれ別のものだからです。
このサーバーのやさしい解説はまだ書いていません。以下はレジストリから読み取った事実です。
使っているAIアプリを選んで、設定をコピーしてください。
HA_URL, HA_TOKEN, HA_ALLOW_WRITE, VOMEHOME_TOKEN「秘密」と表示された値は、あなたのアカウントの鍵です。絶対に人に教えたり、チャットに貼り付けたりしないでください。
必要なもの
どのアプリを使っていますか?
上でアプリを選んでください。選んだアプリを覚えておくので、次からはボタンに「…にインストール」と表示されます。
Claude Desktop → Settings → Developer → Edit Config を開き、claude_desktop_config.json にこれを貼り付けます
{
"mcpServers": {
"home-assistant": {
"command": "npx",
"args": [
"-y",
"@vortitron/home-assistant-mcp"
],
"env": {
"HA_URL": "your-value",
"HA_TOKEN": "your-value",
"HA_ALLOW_WRITE": "your-value",
"VOMEHOME_TOKEN": "your-value"
}
}
}
}ターミナルでこれを実行します
claude mcp add home-assistant --env HA_URL=your-value --env HA_TOKEN=your-value --env HA_ALLOW_WRITE=your-value --env VOMEHOME_TOKEN=your-value -- npx -y @vortitron/home-assistant-mcp動かす前に、空欄の値を入力してください。
プロジェクトの .cursor/mcp.json、または ~/.cursor/mcp.json に貼り付けます
{
"mcpServers": {
"home-assistant": {
"command": "npx",
"args": [
"-y",
"@vortitron/home-assistant-mcp"
],
"env": {
"HA_URL": "your-value",
"HA_TOKEN": "your-value",
"HA_ALLOW_WRITE": "your-value",
"VOMEHOME_TOKEN": "your-value"
}
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
プロジェクトの .vscode/mcp.json に貼り付けます
{
"servers": {
"home-assistant": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@vortitron/home-assistant-mcp"
],
"env": {
"HA_URL": "your-value",
"HA_TOKEN": "your-value",
"HA_ALLOW_WRITE": "your-value",
"VOMEHOME_TOKEN": "your-value"
}
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
これはパソコンで動くサーバーですが、ChatGPTがつなげるのはインターネット上のサーバーだけです。ほかのアプリを選んでください。
選んだアプリは、この端末のCookieに保存されます。アカウントは不要です。
HA_URL envHA_ALLOW_WRITE envこの設定は、作者のレジストリ登録情報から作成しています。READMEと違う場合は、READMEに従ってください。
パソコンで動くサーバーです。インストールすると、ツール一覧がAIアプリに表示されます。
誰でも見られる情報をチェックしており、コードは読んでいません。当てはまらない項目は数に入れていません。 · 2026年11月8日にチェック
レジストリ名は、リポジトリを所有するGitHubアカウント Vortitron で確認済みです
このリポジトリはまだGitHubから読み取っていません
このリポジトリはまだGitHubから読み取っていません
これはパソコンで動くため、インターネット上のエンドポイントはありません
パソコンで動き、代わりにローカルの設定を使います
パソコンで動くサーバーです。ツール一覧を読み取れるのは、インターネット上のエンドポイントがある場合だけです
レジストリでこのカテゴリにある有効なすべてのサーバーと比較しています。スターは、公開者がリポジトリの所有者である場合だけ数えます。
当てはまる基本チェック1項目のうち1項目に合格しました。コードは読んでいません。キーやトークンを追加する前に、サーバーがどんなアクセスを求めているかを確認し、必要な権限だけを持つキーを使ってください。
入力が必要なもの:HA_TOKEN, VOMEHOME_TOKEN
あなたのパソコンで動きます。必要なときにAIアプリが起動し、データは作者のサーバーを通りません(サーバー自体がオンラインサービスを呼び出す場合を除きます)。
GitHubリポジトリの最終更新は–、最新バージョン(0.17.3)がレジストリに届いたのは3 日前です。
Claude Desktop、Claude Code、Cursor、VS CodeなどのMCP対応アプリで使えます。パソコンにNode.jsも必要です。
同じカテゴリには:GitHub, Desktop Commander, Cloudflare MCP
同じカテゴリで、ほかの作者が作ったサーバー。スターの多い順。
カードの見方:★ GitHubスターi3つの柱:レビュー · チェック · 利用状況i更新=最新バージョンをレジストリに公開した日i
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
MCP server for terminal commands, file operations, and process management
Cloudflare MCP servers
作者のリポジトリから書かれたとおりにコピーしたものです。PopNx MCPは内容を確認・推奨していません。HTML、画像、スクリプトは取り除いています。リンクはこのサイトの外へ移動します。
A Model Context Protocol (MCP) server that lets coding agents — Cursor, VS Code (Copilot), Claude Desktop and anything else that speaks MCP — talk directly to Home Assistant and (optionally) the ESPHome dashboard.
Instead of copy-pasting entity ids, YAML and current values into your agent, the agent can discover entities, read live state, render templates, call services and edit automations itself — and iterate until the code actually works.
In Claude Code, four side panes show what Claude is doing to your home as it happens: the automation it is working on, the ESPHome device it is building, the home's health score and a dashboard that works. One command installs all four (below).
Part of the Vome family and an open-source companion to
VomeHome (managed Home Assistant). It is useful stand-alone for any Home
Assistant user.
A typical "change an automation" loop today looks like: you tell the agent which entities exist, paste their current values, paste the YAML, apply the change, then manually check whether it worked. With this server the agent does all of that:
All write operations are off by default and gated behind an explicit safety policy (see Safety).
| Tool | Description |
|---|---|
ha_get_config | Core config: version, location, time zone, loaded components. |
ha_list_entities | List entities (filter by domain, free-text search, area). |
ha_get_state | Full state + attributes for one or more entities. |
ha_get_history | Historical state changes over a time window. Given only a start time, it runs up to now (Home Assistant alone stops 24 hours after the start); ha_get_logbook does the same. |
ha_list_services | Available services (and their fields for a given domain). |
ha_list_areas | Areas (rooms/zones). |
ha_list_devices | Device registry (filter by area / search). |
ha_get_entity_registry | Registry metadata: platform, area, device, disabled/hidden. |
ha_render_template | Render a Jinja2 template against live state. |
ha_list_helpers | List stored helpers (input_boolean, input_number, counter, timer, …). |
ha_list_automations | Automations with entity_id, unique id, state, last-triggered. |
ha_get_automation | Full automation config (triggers/conditions/actions) for an automation made in the editor. One written in a YAML package or included file is named as such, with what to search for to find its file. |
ha_check_config | Validate the configuration (Check configuration). |
ha_wait_until_running | Wait (up to 120 s) for Home Assistant to finish restarting, checking its core state every 5 s. While it restarts, the other tools say "Home Assistant is restarting (core state: …)" or "not answering — it may be restarting" instead of a raw 502, nginx 404 or WebSocket error. When the home is a CHAP pair's main and its standby is running the home (failover), they say that instead, name the standby and how to reach it (instance_id on the call, or vomehome_use_instance); the CHAP status is asked once per half minute at most, and only for restart-shaped failures. |
ha_get_system_log | Deduplicated, structured errors — level, logger, source, count, first/last seen. Start here. |
ha_get_error_log | Tail of the raw Home Assistant error log. |
ha_get_supervisor_log | Add-on / Core / Supervisor / host logs (HAOS or Supervised). |
ha_list_media_files / ha_read_media_file | Read-only look into /media: a saved camera snapshot comes back as an image (needs ha:files, and Vome add-on 0.3.66 / integration 0.9.51 on the home). |
ha_camera_image | A camera's current still, as an image the agent can see. Via VomeHome the key needs Cameras ticked. |
ha_camera_frame | A camera still decoded and shrunk to a small grid of RGB pixels, for clients that draw pictures in text. |
ha_view_snapshot | Everything a dashboard view shows in one call: states, rendered templates, history in few points, camera frames. For dashboard clients. |
ha_watch_states | Wait for state changes instead of polling: the home's Vome component sends them as they happen (through VomeHome). Where no component is connected (a hosted home without the Vome add-on, a direct connection) it reads the states every ~3 s for the same wait and answers in the same shape with mode: "polling"; a 401/403 is never papered over. |
ha_get_logbook | Human-readable logbook entries, filtered by entity_id, contains (message, name or entity_id), name (e.g. Vome) and domain. At most limit (default 500) come back, the newest, with count_before_limit, truncated and older_entries_end_time to read further back. A window longer than a day is read a day at a time, newest first, stopping as soon as limit entries match (at most 31 days per call), so Home Assistant is never asked for more than 24 hours at once. |
ha_get_energy_prefs | The Energy dashboard's setup (grid, solar, battery, gas, water, tracked devices) with the dashboard's own validation. |
ha_list_traces | Recent automation/script runs and how each one stopped. |
ha_get_trace | Step-by-step detail for one run, with failed_at naming the blocking step. |
Write-gating depends on the mode. In direct mode the MCP is the only guard,
so these refuse until
HA_ALLOW_WRITE=true. In brokered mode your VomeHome
API key carries the per-instance
ha:write/ha:configscopes and the server
enforces them, so the client flags are optional local-only restrictions.
| Tool | Description |
|---|---|
ha_call_service | Call any service (turn_on, set_temperature, …). A service that can return a response (shell_command's stdout/stderr/returncode, script, weather.get_forecasts …) is asked for it, and it comes back as service_response. |
ha_speech_to_text | Run a WAV (16-bit PCM, at most 30 s) through one of the home's speech-to-text engines (stt.*) and get back the words it heard, to test an assistant's hearing without speaking to a device. audio_path reads a local file (npx servers only); audio_base64 sends the bytes (the hosted MCP). Language defaults to the home's own. Engines want 16 kHz mono (ffmpeg -i in.wav -ar 16000 -ac 1 -sample_fmt s16 out.wav). A write because some engines (Vome Hearing, cloud ones) charge per request: needs HA_ALLOW_WRITE / ha:write; not for external homes through VomeHome. |
ha_clear_system_log | Empty the structured error store (only needs HA_ALLOW_WRITE). |
ha_set_log_level | Change logging for one integration at runtime (only needs HA_ALLOW_WRITE). |
ha_set_automation | Create or update an automation (also needs HA_ALLOW_CONFIG_WRITE). |
ha_set_helper | Create or update a helper — no configuration.yaml, no restart. |
ha_read_config_file | Read a file under the config directory — text by default, or encoding: 'base64' for a binary asset (needs ha:files). |
ha_write_config_file | Replace a file under the config directory — text by default, or encoding: 'base64' for a binary asset; checks the config and restores the file if it fails (needs ha:files). |
ha_upload_file | Copy a file already on disk (a web page, an image, a package) into the config directory: read from the MCP server's own filesystem, sent as text or base64 as it needs, at most 2 MiB, written and checked like ha_write_config_file. Local (npx) servers only — the hosted MCP can't see your files and answers with the equivalent curl upload (needs ha:files). |
ha_delete_config_file | Delete one file under the config directory. Never a directory, and never configuration.yaml, secrets.yaml or Home Assistant's database. Names its target home like a write (needs ha:files, and Vome add-on 0.3.55 / integration 0.9.39 on the home). |
ha_edit_config_file | Change part of a text file in place: exact find-and-replace edits that must each match once, then the same check-and-restore as a write. For a three-line change to a large file (needs ha:files). |
ha_list_config_files | List a directory under the config directory, folders first: glob filters by name (*.yaml) or path (**/*.html), offset/limit page (default 200), and the reply gives total_entries, total_bytes (this folder's own files, not subfolders) and truncated when the home stopped at its 500-entry cap (needs ha:files). |
ha_move_config_file | Move or rename one file under the config directory, creating folders on the way; never overwrites unless asked. Names its target home like a write (needs ha:files, and Vome add-on 0.3.66 / integration 0.9.51). |
ha_delete_helper | Delete a stored helper. Refuses when the id looks shared with a configuration.yaml helper, because Home Assistant would take that entity down with it. |
ha_delete_automation | Delete an automation (also needs HA_ALLOW_CONFIG_WRITE). |
ha_get_script / ha_set_script / ha_delete_script | Scripts by id, the same way as automations: put a step several automations share in one script. Writes need HA_ALLOW_CONFIG_WRITE. |
ha_update_entity | Rename, re-id, move, re-icon, disable or hide an entity in the registry (needs HA_ALLOW_CONFIG_WRITE). |
ha_update_device | Rename a device, move it to an area, disable it or set its labels (needs HA_ALLOW_CONFIG_WRITE). |
ha_expose_entities | List or change what Assist, Alexa and Google Assistant can see and control; listing needs only read (changing needs HA_ALLOW_CONFIG_WRITE). |
ha_set_energy_prefs | Change the Energy dashboard's setup; each list passed replaces that list whole, then it is validated (needs HA_ALLOW_CONFIG_WRITE). |
ha_get_statistics | Read long-term statistics (what the Energy dashboard draws) per 5 minutes to month; largest_changes lists the biggest buckets, like the Outliers button. |
ha_adjust_statistic | Correct one 5-minute bucket of a statistic, by new value or by adjustment, as Developer Tools → Statistics does (needs HA_ALLOW_CONFIG_WRITE). |
ha_remove_entity | Remove an orphaned registry entry (needs HA_ALLOW_CONFIG_WRITE). |
ha_matter_reinterview | The Matter device page's Re-interview, for a device whose endpoints changed after a firmware update (needs HA_ALLOW_CONFIG_WRITE). |
ha_trigger_automation | Manually run an automation now. |
ha_reload_automations | Reload automations without restarting. |
| Tool | What it does |
|---|---|
ha_list_dashboards | List dashboards (url_path, title, mode, sidebar). |
ha_get_dashboard | Read one dashboard's full config (views, cards, …). |
ha_save_dashboard | Save/replace a dashboard config (needs HA_ALLOW_CONFIG_WRITE). |
ha_create_dashboard | Register a new storage-mode dashboard (needs HA_ALLOW_CONFIG_WRITE). |
| ha_update_dashboard | Change a dashboard's title, icon, sidebar
冒頭だけを表示しています。続きはリポジトリで読めます