Navigation
MCP Apple Notes: Conversational Queries & Smart Insights - MCP Implementation

MCP Apple Notes: Conversational Queries & Smart Insights

MCP Apple Notes: Conversate with your Apple Notes in Claude. RAG-powered smart queries, analysis, and insights via Model Context Protocol. Effortless intelligence, made seamless.

Knowledge And Memory
4.1(181 reviews)
271 saves
126 comments

Ranked in the top 6% of all AI tools in its category

About MCP Apple Notes

What is MCP Apple Notes: Conversational Queries & Smart Insights?

Designed to integrate Apple Notes with AI assistants like Claude, this MCP (Model Context Protocol) server enables semantic search and retrieval-augmented generation (RAG) directly from your notes. By leveraging local vector embeddings and LanceDB storage, it allows conversational AI to dynamically reference your notes without relying on cloud APIs.

How to use MCP Apple Notes: Conversational Queries & Smart Insights?

  • Clone repository and install dependencies using bun
  • Configure Claude Desktop to connect to the local server via developer settings
  • Initiate note indexing with natural language commands like "Index my notes"
  • Ask queries like "Find my meeting notes from last week" to retrieve relevant content

MCP Apple Notes Features

Key Features of MCP Apple Notes: Conversational Queries & Smart Insights?

  • On-device processing ensures privacy with no data leaving your machine
  • Real-time semantic search using state-of-the-art embedding models
  • Full text search capability for precise keyword matching
  • Native Apple Notes integration through JavaScript for Automation (JXA)
  • Configurable server for advanced users wanting custom setups

Use cases of MCP Apple Notes: Conversational Queries & Smart Insights?

Power users can:

  • Perform cross-note analysis to identify patterns in project documentation
  • Automate note organization using AI-driven categorization
  • Create summaries of meeting notes by querying specific dates/topics
  • Extract key insights from large volumes of personal or work-related notes

MCP Apple Notes FAQ

FAQ

  • How to check server status? Use tail -f server.log for real-time output
  • Why use local embeddings? Maximizes privacy and reduces latency for real-time responses
  • Can I use other AI models? MCP protocol compatibility allows integration with any supported LLM
  • Storage limits? Performance scales with available RAM but handles tens of thousands of notes

Content

MCP Apple Notes

MCP Apple Notes

A Model Context Protocol (MCP) server that enables semantic search and RAG (Retrieval Augmented Generation) over your Apple Notes. This allows AI assistants like Claude to search and reference your Apple Notes during conversations.

MCP Apple Notes

Features

  • 🔍 Semantic search over Apple Notes using all-MiniLM-L6-v2 on-device embeddings model
  • 📝 Full-text search capabilities
  • 📊 Vector storage using LanceDB
  • 🤖 MCP-compatible server for AI assistant integration
  • 🍎 Native Apple Notes integration via JXA
  • 🏃‍♂️ Fully local execution - no API keys needed

Prerequisites

Installation

  1. Clone the repository:
git clone https://github.com/RafalWilinski/mcp-apple-notes
cd mcp-apple-notes
  1. Install dependencies:
bun install

Usage

  1. Open Claude desktop app and go to Settings -> Developer -> Edit Config

Claude Desktop Settings

  1. Open the claude_desktop_config.json and add the following entry:
{
  "mcpServers": {
    "local-machine": {
      "command": "/Users/<YOUR_USER_NAME>/.bun/bin/bun",
      "args": ["/Users/<YOUR_USER_NAME>/apple-notes-mcp/index.ts"]
    }
  }
}

Important: Replace <YOUR_USER_NAME> with your actual username.

  1. Restart Claude desktop app. You should see this:

Claude MCP Connection Status

  1. Start by indexing your notes. Ask Claude to index your notes by saying something like: "Index my notes" or "Index my Apple Notes".

Troubleshooting

To see logs:

tail -n 50 -f ~/Library/Logs/Claude/mcp-server-local-machine.log
# or
tail -n 50 -f ~/Library/Logs/Claude/mcp.log

Todos

  • Apple notes are returned in the HTML format. We should turn them to Markdown and embed that
  • Chunk source content using recursive text splitter or markdown text splitter
  • Add an option to use custom embeddings model
  • More control over DB - purge, custom queries, etc.
  • Storing notes in Notes via Claude

Related MCP Servers & Clients