Agent-Native Calendar
Agent-Native Google Calendar - manage events, sync, and public booking
作者による説明(英語の原文)
Control Windy Word voice-to-text from any MCP agent — 60 tools across 12 categories.
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。
WINDY_WORD_MCP_HOST, WINDY_WORD_MCP_PORT, WINDY_WORD_MCP_TIMEOUT_MS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": {
"windy-word": {
"command": "npx",
"args": [
"-y",
"windy-word-mcp"
],
"env": {
"WINDY_WORD_MCP_HOST": "your-value",
"WINDY_WORD_MCP_PORT": "your-value",
"WINDY_WORD_MCP_TIMEOUT_MS": "your-value"
}
}
}
}ターミナルでこれを実行します
claude mcp add windy-word --env WINDY_WORD_MCP_HOST=your-value --env WINDY_WORD_MCP_PORT=your-value --env WINDY_WORD_MCP_TIMEOUT_MS=your-value -- npx -y windy-word-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": {
"windy-word": {
"command": "npx",
"args": [
"-y",
"windy-word-mcp"
],
"env": {
"WINDY_WORD_MCP_HOST": "your-value",
"WINDY_WORD_MCP_PORT": "your-value",
"WINDY_WORD_MCP_TIMEOUT_MS": "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": {
"windy-word": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"windy-word-mcp"
],
"env": {
"WINDY_WORD_MCP_HOST": "your-value",
"WINDY_WORD_MCP_PORT": "your-value",
"WINDY_WORD_MCP_TIMEOUT_MS": "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。
WINDY_WORD_MCP_HOST envWINDY_WORD_MCP_PORT envWINDY_WORD_MCP_TIMEOUT_MS 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9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 sneakyfree 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。
レジストリには必須のキーは載っていません。ただし、最初に使うときにサインインを求めるサーバーもあります。
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(1.3.0)がレジストリに届いたのは6 か月前です。
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:Agent-Native Calendar, Excel MCP Server, MCP Server for Excel
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:↓ 週あたりのダウンロードi★ 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
Agent-Native Google Calendar - manage events, sync, and public booking
Create and edit Excel files with AI: charts, PivotTables, formulas. No Excel needed.
Excel automation for AI - Sheets, Power Query, DAX, VBA, Tables, Ranges and more. Windows only.
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。
An MCP (Model Context Protocol) server that turns Windy Word — the voice-to-text desktop app — into an agent-controllable platform. 115 tools spanning paste / hotkeys / transcription / recording verbs / audio devices / install / diagnostics / archive / voice clones / translation / documents / system / window / account + billing / TTS / settings-undo / music-ducking / bulk-clone-ingest / soul-file export.
Windy Word ships a local HTTP control server on 127.0.0.1:18765. This package is a schema-validated MCP wrapper around it. Agents call MCP tools; the server forwards to Windy Word over localhost; everything happens on the user's machine (no network round-trips for state queries).
For most users:
claude mcp add windy-word --command "npx" --args "-y" "windy-word-mcp"
Or in ~/.claude.json / ~/.config/claude/claude_desktop_config.json:
{
"mcpServers": { "windy-word": { "command": "npx", "args": ["-y", "windy-word-mcp"] } } }
Local-dev (cloned repo):
git clone https://github.com/sneakyfree/windy-word-mcp && cd windy-word-mcp
npm install claude mcp add windy-word --command "node" --args "$(pwd)/bin/windy-word-mcp.js"
| Variable | Default | Purpose |
|---|---|---|
WINDY_WORD_MCP_HOST | 127.0.0.1 | Override the control-server host |
WINDY_WORD_MCP_PORT | 18765 | Override the control-server port |
WINDY_WORD_MCP_TIMEOUT_MS | 5000 | Default per-request timeout (the install + transcribe tools override this internally for long ops) |
Regenerate this section's tool count any time with
npm run test:list-tools
(
node scripts/list-tools.js), which enumerates the live server's registered tools.
| Tool | What it does |
|---|---|
get_platform | OS, arch, distro, display server, desktop env, xdotool/ydotool presence |
12 platform-specific paste backends (macOS / Windows / Linux X11 / Linux Wayland) with capability metadata, hotkey-collision auto-detection, and a verified fallback chain.
| Tool | What it does |
|---|---|
list_paste_strategies | All 12 strategies + per-strategy availability + resolved chain + collision flag |
get_active_paste_strategy | Current selection + resolved chain |
set_paste_strategy | Switch active (or "auto") |
test_paste_strategy | Fire a specific strategy at the focused window (injects text!) |
auto_paste | Run the auto-execute chain with explicit candidates |
run_paste_injection_test | Real end-to-end test — spawns Tk target, fires paste, diffs result |
get_paste_history / clear_paste_history | In-memory audit log |
get_paste_target | XWayland vs Wayland-native detection |
| Tool | What it does |
|---|---|
list_hotkeys | Current bindings + available actions + reserved combos |
set_hotkey | Rebind a global shortcut (Electron accelerator format) |
reset_hotkeys | Restore all global shortcuts to catalog defaults + re-register |
| Tool | What it does |
|---|---|
list_models | Whisper model catalog + current + WindyTune ladder |
set_model | Switch (hot-reloads Python engine over WebSocket) |
get_windytune_state | Auto-tune state, ladder, recent-timing history |
| Tool | What it does |
|---|---|
start_recording | Begin a mode-aware recording (batch / streaming / API engine) |
stop_recording | End the recording → trigger transcription + paste pipeline |
cancel_recording | Abort an in-flight recording without saving |
get_recording_state | isRecording + pythonEngineRunning + mode snapshot |
toggle_recording | Start/stop (same effect as the global hotkey) |
paste_transcript | Re-paste the most recent transcript |
set_language | Set the Whisper transcription language (ISO 639-1) |
set_panel_visibility | Configure a bottom panel row (always / hover / off) |
| Tool | What it does |
|---|---|
list_audio_devices | Enumerate microphones available to Windy Word |
install_dependency family (8)Agent installs missing system tools (Linux/macOS/Windows package managers). Linux uses pkexec; macOS uses user-scope brew; Windows uses winget. Whitelist-only: wtype, ydotool, wl-clipboard, xdotool, cliclick, ffmpeg.
| Tool | What it does |
|---|---|
list_installable_dependencies | What's installable on this machine right now |
install_dependency | Synchronous install (whitelist + dryRun) |
install_dependency_async | Fire-and-poll variant — returns jobId |
get_install_status | Poll a job |
list_install_jobs | All in-memory jobs |
get_install_history / clear_install_history | Audit log |
setup_install_polkit_rule | Install/remove the Linux polkit auto-approve rule |
Polkit setup (Linux): setup_install_polkit_rule installs /etc/polkit-1/rules.d/49-windy-install-deps.rules once per machine to make installs prompt-free. See the rule snippet.
13 local rule-based checks covering paste-stack tooling, /dev/uinput permissions, polkit rule presence (with EACCES-tolerant detection), Python engine liveness, Mutter hotkey collision, macOS Accessibility + Microphone permissions, Homebrew presence, cliclick presence.
| Tool | What it does |
|---|---|
run_diagnostics | Run the local battery; return structured findings + actionable remediations |
list_diagnostic_checks | What checks exist + which apply to this platform |
cloud_diagnose | LLM-augment via the windy-fix-me Cloudflare Worker (Claude Haiku 4.5 via OpenRouter) |
49 typed catalog entries with tags (archive, voice-clone, transcription, paste, hotkey, ui, geometry, lifecycle, license). Validation runs server-side before any write.
| Tool | What it does |
|---|---|
list_settings | Catalog + current live values + available tags. Supports ?tag=X filter |
describe_setting | Single entry + current value |
set_setting | Validate + apply + return side effects |
get_config | The settings an agent may read, by path (personal values redacted; tokens and consent never returned) |
set_config | Retired: answers retired, use set_setting |
| Tool | What it does |
|---|---|
undo_last_setting_change | Revert the most recent catalog-validated setting change this session |
list_recent_setting_changes | List session setting changes, oldest first |
Agents work with opaque arc:YYYY-MM-DD:HHMMSS.md ids, never filesystem paths. Path-confined deletes.
| Tool | What it does |
|---|---|
list_archive_entries | List recordings with transcripts + metadata |
get_archive_stats | totalFiles/sizeMB/days/words/sessions (30s server-side cache) |
read_archive_entry | Base64 audio or video for an entry |
delete_archive_entry | Tear down md + audio + video |
open_archive_folder | Pop OS file manager at the archive root |
search_archives | Full-text substring search across every transcript |
archives_by_date_range | Sessions whose start timestamp falls within [from, to] |
bulk_delete_archives | Tear down multiple entries in one call |
| Tool | What it does |
|---|---|
list_voice_clones | All clones + activeId (no audio bytes) |
get_active_voice_clone | Currently-active clone (or null) |
set_active_voice_clone | Switch active (or deactivate with null) |
create_voice_clone_from_path | Create from an audio file on disk (path-confined copy) |
delete_voice_clone | Irreversible teardown |
preview_voice_clone | Metadata + optional base64 audio |
list_clone_bundles | Training-bundle catalog |
submit_voice_clone_to_cloud | Submit a local clone to Windy Clone for ElevenLabs training |
get_cloud_clone_order_status | Poll Windy Clone for ElevenLabs training progress |
bulk_ingest_to_clone | Copy a batch of audio files into the voice-samples store as clones |
| Tool | What it does |
|---|---|
scan_folder_for_media | Scan a folder (recursive) for audio + video files |
watch_folder_for_recordings | Start/stop a folder watcher that auto-ingests new audio |
list_clone_watchers | List active folder watchers |
| Tool | What it does |
|---|---|
translate_text | TM-cache-first → Groq/OpenAI fallback (auto-populates cache) |
lookup_translation_memory | Local cache query, no API |
save_translation_memory | Manual upsert |
get_translation_memory_stats | Total / topPairs / recentEntries |
clear_translation_memory | Wipe (destructive) |
| Tool | What it does |
|---|---|
extract_document_text | Path-based, supports txt/md/csv/html/pdf/docx (5MB default, 20MB cap) |
save_text_file | Path-based write; refuses overwrite unless flagged |
transcribe_audio_file | Any audio file → Whisper transcript via warm WebSocket engine (~5× real-time on CPU) |
| Tool | What it does |
|---|---|
get_sound_effect_state | Per-hook-stage enabled/volume settings (6 lifecycle stages) |
set_sound_hook | Configure a single sound-effect hook stage |
set_active_sound_pack | Switch the active sound pack |
set_master_sfx_volume | Set master SFX volume (0-100) |
set_sound_effect_mode | Switch EffectsEngine mode (silent / classic / surprise / custom / pack) |
list_sound_effect_packs | List known sound-effect packs |
get_widget_state | Mini-widget (tornado) runtime state via the renderer bridge |
| Tool | What it does |
|---|---|
detect_hardware | RAM, CPU, GPU (nvidia-smi + Apple Silicon detect), disk free |
get_autostart_status | Is Windy Word configured to launch on login |
set_autostart | Toggle login-item / .desktop entry |
export_soul_file_to_path | Forma Animae: zip the whole archive (audio + video + transcripts + manifest) for the digital-twin pipeline |
| Tool | What it does |
|---|---|
get_window_state | Snapshot of maximized/minimized/focused/visible/fullScreen |
minimize_window / maximize_window / unmaximize_window | Title-bar window controls |
bring_window_to_front | Restore + show + raise (does not steal keyboard focus) |
set_window_geometry | Set position + size in screen pixels (live + persisted) |
set_video_fullscreen | Toggle native OS-level fullscreen |
set_always_on_top | Keep the window above others |
set_opacity | Set window opacity (0.1-1.0) |
set_theme | dark / light / auto |
set_font_size | UI zoom factor (70-150%) |
show_hide_window | Cycle main → tornado → hidden → main |
quick_translate | Open the Quick Translate mini-window |
restart_app / quit_app | Relaunch / quit Windy Word (destructive) |
| Tool | What it does |
|---|---|
get_version | Windy Word + Electron + Node versions |
check_for_updates | Trigger electron-updater's update check |
set_analytics_enabled | Opt in/out of anonymous usage analytics |
open_url | Open an http/https URL or a Windy ecosystem scheme |
send_notification | Show an OS-native notification |
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