Windy Word MCP server
io.github.sneakyfree/windy-word-mcp·v1.3.0·1 starsControl Windy Word voice-to-text from any MCP agent — 60 tools across 12 categories.
1 stars
Reviews
Write oneNobody has reviewed Windy Word yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Windy Word tools (63, 10 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
auto_pastewrite actionExecute the auto-paste flow against an explicit candidate chain. Returns the winning
clear_install_historyWipe the in-memory install audit log. Useful between test runs.
clear_paste_historyReset the in-memory paste history buffer. Useful between stress-test runs.
clear_translation_memoryWipe the entire translation-memory cache. Destructive — confirm with the user before calling.
cloud_diagnosewrite actionRun local diagnostics AND route the findings to the windy-fix-me cloud-relay for LLM-augmented
create_voice_clone_from_pathwrite actionCreate a voice clone from an audio file on disk. Copies the source file into Windy Word's
delete_archive_entrywrite actionTear down an archive entry: removes the transcript .md file + linked audio + linked video, all
delete_voice_clonewrite actionDelete a voice clone (metadata + audio file on disk). If the deleted clone was the active one,
describe_settingReturn the full catalog entry for one setting (type / allowed values / description / default /
detect_hardwareReturn system hardware info: totalRAM (GB), freeRAM (GB), cpuModel, cpuCores, platform, arch,
export_soul_file_to_pathExport the user's entire Windy Word archive (audio + video + transcripts) as a single zip file
extract_document_textExtract plain text from a document file at a given path. Supports .txt / .md / .csv (read as
get_active_paste_strategyReturn the currently selected paste strategy, the user-configured fallback chain, and
get_active_voice_cloneReturn the currently-active voice clone (the one used for TTS playback), or {active: null} if no
get_archive_statsReturn aggregate stats for the user's recording archive: totalFiles, totalSizeMB, days (number of
get_autostart_statusCheck whether Windy Word is configured to auto-launch on user login. Returns {platform, enabled,
get_cloud_clone_order_statuswrite actionCheck the status of a Windy Clone cloud-training order — used after submit_voice_clone_to_cloud
get_configReturn the full electron-store config tree (every setting Windy Word has persisted).
get_install_historyReturn the audit log of recent install_dependency attempts on this machine (timestamp,
get_install_statusReturn the current state of an async install job started by install_dependency_async. Status is
get_paste_historyReturn the last N paste attempts with diagnostic data: timestamp, text length, content
get_paste_targetDetect whether the currently focused window is XWayland or Wayland-native (or unknown).
get_platformReturn OS / arch / distro / display-server / desktop-environment / tool-availability
get_sound_effect_stateReturn the current sound-effects configuration: per-hook-stage enabled/volume settings (the 6
get_translation_memory_statsReturn TM cache stats: totalEntries, topPairs (top 10 source→target language pairs by count),
get_widget_stateReturn mini-widget (tornado) runtime state via the renderer bridge: whether the WidgetEngine is
get_windytune_stateReturn WindyTune auto-tune state: whether it is enabled, the current model, the model
install_dependencyInstall a missing system tool via the distro package manager wrapped in pkexec.
install_dependency_asyncFire-and-poll variant of install_dependency. Returns a jobId immediately and runs the install in
list_archive_entriesList archived recording sessions (the user's historical transcripts + linked audio/video). Each
list_clone_bundlesList training-bundle catalog — audio/video recordings the user has marked as candidates for
list_diagnostic_checksList the catalog of Windy Doctor diagnostic checks without running them. Returns each check's
list_hotkeysList all current keyboard shortcut bindings, the set of rebindable actions, and the
list_install_jobsList all install jobs currently in memory — both running and recently completed. Useful for dashboards or
list_installable_dependenciesList the whitelisted system tools that Windy Word can install on this machine to
list_modelsList available Whisper transcription models (tiny / base / small / medium / large-v3),
list_paste_strategiesList all 12 paste strategies (macOS / Windows / Linux X11 / Linux Wayland) with full
list_settingsList every setting Windy Word exposes as an agent-discoverable, schema-validated path. Returns
list_sound_effect_packsList the sound-effect packs the Windy Word EffectsEngine knows about (_silent, classic-beep,
list_voice_clonesList all voice clones the user has on this machine. Returns each clone's id, name, duration,
lookup_translation_memoryLook up a (text, sourceLang, targetLang) tuple in the local translation-memory cache. Returns
open_archive_folderPop the archive root directory in the user's OS file manager. Side-effect on the desktop
preview_voice_cloneReturn a voice clone's metadata, optionally with the base64-encoded audio sample. Pass
read_archive_entryReturn an archive entry's metadata + optionally the base64 audio or video media bytes. The
run_diagnosticswrite actionRun the local Windy Doctor check battery and return a structured report: overall health
run_paste_injection_testwrite actionReal end-to-end paste injection test. Spawns a focusable Tk scratchpad target, temporarily
save_text_filewrite actionWrite text content to a file at a given path. Default: refuses to overwrite existing files (returns
save_translation_memoryStore a (source, target, sourceLang, targetLang) tuple in the TM cache. Useful when an agent has
set_active_sound_packSwitch the active sound pack. Pack ids come from list_sound_effect_packs — typical built-ins are
set_active_voice_cloneSet which voice clone is the active TTS default. Pass id=null to deactivate (no clone — falls back
set_autostartEnable or disable Windy Word's auto-launch on user login. Linux writes/removes a .desktop
set_configwrite actionPatch the config store. Pass EITHER {path, value} for a single dotted-path write
set_hotkeyRebind a keyboard shortcut. Action keys: toggleRecording, pasteTranscript,
set_master_sfx_volumeSet the master SFX volume (0-100). Affects every hook stage as a multiplier on per-stage volumes.
set_modelSwitch the active transcription model. Hot-reloads the running Python engine over
set_paste_strategySelect a paste strategy. Pass "auto" to use the platform default chain, or a specific
set_settingValidate and apply a setting change against the catalog. Rejects unknown paths, type mismatches,
set_sound_effect_modeSwitch the EffectsEngine mode: "silent" (no sounds), "classic" (built-in beeps), "surprise"
set_sound_hookConfigure a single sound-effect hook stage. Hooks are the 6 lifecycle points where Windy Word
setup_install_polkit_ruleInstall or remove the Linux polkit auto-approve rule that lets install_dependency run without
test_paste_strategyWARNING: injects test text ("wtest") into whatever window currently has focus.
transcribe_audio_fileTranscribe an audio file at a given path. Accepts any format ffmpeg can read (wav, mp3, m4a,
translate_textTranslate text to a target language. Tries the local translation-memory cache first (instant +
Public scan report
scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it
- Code scan4 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 27 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How Windy Word compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 92/100
- higher than 90% of 4,460 AI and agents servers
- Tools
- 63
- the typical AI and agents server has 6
- Tools that change things
- 16%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 1
- more than 50% of 2,711 AI and agents servers
What its tools let an agent do: 38 read · 4 create · 15 change · 2 delete · 4 run or deploy
Install Windy Word in Claude Code, Cursor or VS Code
Runs npx -y windy-word-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add windy-word-mcp -- npx -y windy-word-mcp
What the publisher says
From the Windy Word repository's README, as published. We do not edit it. Read it on GitHub
windy-word-mcp
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).
Install
For most users:
claude mcp add windy-word --command "npx" --args "-y" "windy-word-mcp"Or in ~/.claude.json / ~/.config/claude/claudedesktopconfig.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"Requirements
- Node.js ≥ 18
- Windy Word running locally (Electron app — the HTTP control server binds automatically at startup)
Environment overrides
Tool catalog (115 tools, 22 categories)
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.
Platform (1)
Paste strategies (9)
12 platform-specific paste backends (macOS / Windows / Linux X11 / Linux Wayland) with capability metadata, hotkey-collision auto-detection, and a verified fallback chain.
Hotkeys (3)
Transcription engine (3)
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Windy Word: common questions
- Is Windy Word MCP server safe?
- Yes, by our scan: it is graded A (92/100). Read the Windy Word safety report
- How do I install Windy Word?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Windy Word need an API key?
- No secret keys are declared. It reads 3 settings from the environment.
- Is Windy Word maintained?
- The last commit was 64 days ago (2026-09-01). The latest release is v1.3.0.
- What can I use instead of Windy Word?
- Servers from other publishers that do the same job: agent-device MCP server, agent-device MCP server and LLM Sandbox MCP server.
- How does Windy Word compare with other AI and agents MCP servers?
- safety score 92/100 (higher than 90% of 4,460 AI and agents servers); tools 63 (the typical AI and agents server has 6); tools that change things 16% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Windy Word
Same job from other publishers: the closest match first, then the best rated.
- agent-deviceLet AI agents inspect, control, and debug real iOS, Android, desktop, and TV appsnot reviewedWidely usedA
- agent-deviceOpen source device layer for AI agents: control mobile, web, TV, and desktop apps over MCPnot reviewedWidely usedA
- LLM SandboxSecurely run LLM-generated code in isolated containers across 7 languages and 3 container backends.not reviewedWidely usedA
- PaperBananaGenerate academic diagrams and statistical plots from text using multi-agent AI.not reviewedEstablishedA
- Agent-Native ClipsScreen recording, meeting notes, and voice dictation - all with AInot reviewedEstablishedA