This MCP server provides programmatic access to Apple Voice Memos on macOS, allowing AI assistants to interact with voice recordings.
From the registry: Access Apple Voice Memos on macOS. List, get audio, extract and generate transcripts.
Please install the `apple-voice-memo-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **macOS Sonoma+** — Requires macOS Sonoma (14.0) or later; Sequoia recommended for transcription
- **Node.js 18+** — Node.js 18 or newer
- **Full Disk Access** — Grant Full Disk Access to your terminal/MCP host so the server can read the Voice Memos database
- **Open Voice Memos app once** — Voice Memos app must have been opened at least once
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","apple-voice-memo-mcp"]
Note: Speech Recognition permission prompted on first use of transcribe_memo. Pairs with whisper-mcp for local transcription.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.FULL_DISK_ACCESSrequiredRequired to read the Voice Memos database.