MCP Apple Notes

Example Use Cases

• 1

  Semantically search and retrieve content from a user's local Apple Notes during a conversation.

• 2

  Perform retrieval-augmented generation using locally stored note embeddings without relying on cloud APIs or keys.

• 3

  Index, update, and reference Apple Notes (full-text and vector search) for personal knowledge and context-aware responses.

Description

This project provides a Model Context Protocol (MCP) server that indexes and serves Apple Notes to AI assistants, enabling semantic and full-text search. It uses an on-device sentence-transformers model (all-MiniLM-L6-v2) for embeddings and LanceDB for vector storage, with native Apple Notes access via JXA. The server runs fully locally (no API keys) and is designed for integration with Claude Desktop as a local MCP endpoint. It helps keep note data private while allowing retrieval-augmented generation and referenceable citations from your notes.