whispernotes-mcp
Whisper Notes MCP Server & CLI
MCP server and command-line access to Whisper Notes — on-device speech-to-text for Mac and iPhone. Claude and any MCP client can search your transcript history, read transcripts (plain, timestamped, or speaker-labeled), and transcribe audio or video files.
100% on-device. The server speaks over a local Unix socket (0600 permissions) — no open ports, no network interface, no cloud. Your audio and transcripts never leave your Mac.
The MCP server is built into the Whisper Notes Mac app — there is nothing to
npxorpip install. This repository is its documentation and registry home. Canonical docs live at whispernotes.app/cli-mcp (agent-readable markdown: whispernotes.app/cli-mcp.md).
Set up
Download Whisper Notes for Mac 1.5.5 or later — Direct Download (DMG) version (the Mac App Store build does not include the Local API). macOS 14+, Apple Silicon.
Open the app → Settings → Integrations → toggle on Local CLI & MCP.
Click Install CLI in the same section — this puts
whispernotes(and thewnshorthand, when that name is free) in your terminal.
Related MCP server: local-mmcp
Connect Claude or any MCP client
Claude Code — one line:
claude mcp add whispernotes -- whispernotes mcpClaude Desktop — add this to ~/Library/Application Support/Claude/claude_desktop_config.json, then restart Claude Desktop:
{
"mcpServers": {
"whispernotes": {
"command": "/usr/local/bin/whispernotes",
"args": ["mcp"]
}
}
}Use the full path from which whispernotes — GUI apps don't read your shell's PATH. Any other local MCP client (Cursor, etc.) works the same way: command whispernotes, args ["mcp"]. Transport is stdio; there is no HTTP endpoint.
Then just ask:
"Read my last five transcripts and tell me what I should follow up on."
"Find the meeting where we discussed the invoice, and draft a reply email."
"Transcribe ~/Desktop/podcast.mp3 and pull out every action item."
MCP tools
Tool | Parameters | Returns |
|
| Recent transcripts with ids, dates, titles |
|
| Full-text matches with snippets |
|
| One transcript's text |
|
| Your most recent transcript |
|
| Transcribes an audio or video file, saves it to history |
| — | Installed models and which one is active |
Long recordings are paged: when a transcript exceeds max_chars, the response ends with an explicit truncation marker telling the agent which offset to continue from — hour-long meetings never overflow a context window.
CLI
The same binary is a full command-line tool:
$ whispernotes status
WhisperNotes 1.5.5 (340) · SenseVoice Small · ready · 3081 notes
$ whispernotes list --limit 3
9f3c21a8 2026-08-01 09:14 0:42 meeting Weekly sync — pricing review
b2d84e07 2026-07-31 18:03 12:26 recorded Idea dump on the walk home
5a1f9c33 2026-07-30 10:52 47:10 imported interview-with-anna.m4a
$ whispernotes show latest | ollama run llama3 "Summarize the key points:"
$ whispernotes export --format md --audio --output-dir ~/Transcripts
✓ exported 312/312 transcript(s), 312 audio file(s) → /Users/you/TranscriptsCommand | Options | What it does |
| — | App version, active model, readiness, note count |
|
| Recent transcripts, newest first |
|
| Full-text search across your history, with snippets |
|
| Print one transcript (defaults to |
|
| Transcribe an audio or video file, save it to history |
|
| Batch-export transcripts, optionally copying the audio alongside |
|
| List or switch models: |
|
| List or switch transcription language — choices follow the active model |
| — | Run the MCP server on stdio |
| — | CLI version · usage |
Results go to stdout, progress and errors to stderr — safe to pipe or redirect. --json always emits a single JSON object or array. whispernotes help prints the full usage; a misused command replies with its exact usage line. wn is a convenience alias — scripts and agents should call whispernotes, which always exists.
Privacy & security
Transport is a Unix domain socket at
~/Library/Application Support/WhisperNotes/api.sockwith0600permissions — only your macOS user account can connect. No TCP port, no network interface, unreachable from any other machine.Off by default: nothing is served until you enable the toggle in Settings.
MCP clients like Claude ask for your approval before each tool call.
Transcription runs on-device (Parakeet V3, Whisper, SenseVoice on the Neural Engine / MLX); results are stored only in your local history.
Links
Docs: whispernotes.app/cli-mcp · raw markdown for agents: /cli-mcp.md
Download: Whisper Notes for Mac (DMG)
iPhone & Mac App Store: App Store
Website: whispernotes.app · Changelog · Privacy
Support: support@whispernotes.app
License
The contents of this repository (documentation and metadata) are MIT-licensed. Whisper Notes itself — the application, including the embedded MCP server and CLI — is commercial software; see whispernotes.app for terms.
This server cannot be installed
Maintenance
Related MCP Servers
- AlicenseAqualityBmaintenanceMCP server for Apple Notes with semantic search (on-device embeddings via all-MiniLM-L6-v2), full-text search, complete CRUD operations, folder management, and fuzzy title matching. 10 tools. Runs fully locally on macOS — no API keys required.Last updated103312MIT
- Flicense-qualityCmaintenanceLocal multimodal MCP server for vision, document, audio, video, and GUI automation, all processed locally on Apple Silicon for privacy and security.Last updated
- Alicense-qualityDmaintenanceAn MCP server for audio/video transcription using MLX-optimized Whisper models, offering fast performance on Apple Silicon with support for multiple output formats and batch processing.Last updated1MIT
- AlicenseAqualityBmaintenanceAn MCP server that enables LLM agents to list, read, create, update, delete, and search Apple Notes on macOS.Last updated621AGPL 3.0
Related MCP Connectors
Search, read, and write your Apple Notes from ChatGPT/Claude via a local Mac agent + MCP relay.
Agent-native MCP server over the public saagarpatel.dev corpus. Read-only, stateless.
User-owned memory for AI agents, Copilot, Claude, IDEs, CLIs, and chat apps over remote MCP.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/mazzzystar/whispernotes-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server