Read local Apple Notes sqlite database and provide it as a context protocol server for Claude Desktop.

Apple Notes Model Context Protocol Server for Claude Desktop.

Read your local Apple Notes database and provide it to Claude Desktop.

Now Claude can search your most forgotten notes and know even more about you.

Noting could go wrong.

Components

Resources

The server implements the ability to read and write to your Apple Notes.

Tools

The server provides multiple prompts:

  • get-all-notes: Get all notes.
  • read-note: Get full content of a specific note.
  • search-notes: Search through notes.

Missing Features:

  • No handling of encrypted notes (ZISPASSWORDPROTECTED)
  • No support for pinned notes filtering
  • No handling of cloud sync status
  • Missing attachment content retrieval
  • No support for checklist status (ZHASCHECKLIST)
  • No ability to create or edit notes

Quickstart

Install the server

Recommend using uv to install the server locally for Claude.

uvx apple-notes-mcp

OR

uv pip install apple-notes-mcp

Add your config as described below.

Claude Desktop

On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.jsonOn Windows: %APPDATA%/Claude/claude_desktop_config.json

Note: You might need to use the direct path to uv. Use which uv to find the path.

Development/Unpublished Servers Configuration

"mcpServers": {
  "apple-notes-mcp": {
    "command": "uv",
    "args": [
      "--directory",
      "{project_dir}",
      "run",
      "apple-notes-mcp"
    ]
  }
}

Published Servers Configuration

"mcpServers": {
  "apple-notes-mcp": {
    "command": "uvx",
    "args": [
      "apple-notes-mcp"
    ]
  }
}

Mac OS Disk Permissions

You'll need to grant Full Disk Access to the server. This is because the Apple Notes sqlite database is nested deep in the MacOS file system.

I may look at an AppleScript solution in the future if this annoys me further or if I want to start adding/appending to Apple Notes.

Development

Building and Publishing

To prepare the package for distribution:

  1. Sync dependencies and update lockfile:
uv sync
  1. Build package distributions:
uv build

This will create source and wheel distributions in the dist/ directory.

  1. Publish to PyPI:
uv publish

Note: You'll need to set PyPI credentials via environment variables or command flags:

  • Token: --token or UV_PUBLISH_TOKEN
  • Or username/password: --username/UV_PUBLISH_USERNAME and --password/UV_PUBLISH_PASSWORD

Debugging

Since MCP servers run over stdio, debugging can be challenging. For the best debuggingexperience, we strongly recommend using the MCP Inspector.

You can launch the MCP Inspector via npm with this command:

npx @modelcontextprotocol/inspector uv --directory {project_dir} run apple-notes-mcp

Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.

License

This project is licensed under the MIT License. See the LICENSE file for details.

Source Code

The source code is available on GitHub.

Contributing

Send your ideas and feedback to me on Bluesky or by opening an issue.

MCP Server ยท Populars

MCP Server ยท New

    nhadaututtheky

    NeuralMemory

    NeuralMemory stores experiences as interconnected neurons and recalls them through spreading activation, mimicking how the human brain works. Instead of searching a database, memories are retrieved through associative recall - activating related concepts until the relevant memory emerges.

    Community nhadaututtheky
    norrietaylor

    Distillery

    Team knowledge evaporates daily โ€” pairing sessions, debugging context, architectural rationale lost to Slack. Distillery captures it at the point of creation, connects it into a living graph, and surfaces it conversationally. It monitors feeds, tracks what matters to your projects, and alerts you before you know to ask. A team brain that learns.

    Community norrietaylor
    ennisaaaaaaaa-stack

    Tideline ๆฝฎ็—•

    Tideline-Memory is a long-term memory system built for AI Agents. Most agent memory: You ask, it finds. Tideline: The agent wakes up already knowing who he is, not querying "who am I?" every session. Achieving accurate memory hits while also preventing memory from expanding at scale.No compression, no forgetting.

    Get-Concord-AI

    Concord MCP

    Live messaging for coding agents

    Community Get-Concord-AI
    alijancb

    Subio MCP

    Open-source MCP server for discovering fast-growing internet conversations with Subio

    Community alijancb