Advertise
MCP.so
Sign In
A

Apple Notes MCP Server

@disco-trooper

Repository

Basic information

Category

Memory & Knowledge

Transports

stdio

Author

disco-trooper

Submitted by

disco_trooper

About Apple Notes MCP Server

No overview available yet

#macos#mcp#semantic-search#apple-notes#rag

Apple Notes MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "apple-notes": {
      "command": "npx",
      "args": [
        "-y",
        "@disco_trooper/apple-notes-mcp"
      ],
      "env": {
        "EMBEDDING_PROVIDER": "local",
        "EMBEDDING_MODEL": "Xenova/all-MiniLM-L6-v2"
      }
    }
  }
}

Apple Notes MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is Apple Notes Mcp?

Apple Notes Mcp is a Model Context Protocol server that integrates with macOS Apple Notes via JXA (JavaScript for Automation). It provides semantic search, hybrid search, and full CRUD operations, allowing Claude and other MCP clients to read, create, update, delete, and manage Apple Notes through natural language commands. It is intended for macOS users who want AI-assisted note management.

How to use Apple Notes Mcp?

Install globally via npm (npm install -g @disco_trooper/apple-notes-mcp) or clone and build from source with Bun. Run bun run setup to run the setup wizard, which configures embedding providers, API keys, indexing preferences, and optionally adds the server to Claude Code configuration. After setup, tools such as search-notes, create-note, update-note, delete-note, move-note, index-notes, and others are available via MCP clients like Claude Code.

Key features of Apple Notes Mcp

  • Semantic search finds notes by meaning, not keywords.
  • Hybrid search combines vector and keyword search.
  • Full CRUD: create, read, update, delete, and move notes.
  • Incremental indexing re-embeds only changed notes.
  • Dual embedding support: local HuggingFace or OpenRouter API.
  • Claude Code integration works with the Claude Code CLI.

Use cases of Apple Notes Mcp

  • Search for notes by conceptual meaning (e.g., "meeting notes from last week").
  • Create new notes in specific folders via natural language.
  • Retrieve full content of a note by its title.
  • Move notes between folders (e.g., archive old projects).
  • Re-index notes after manual edits to keep search results current.

Frequently asked questions

1

Why do I get "Note not found"?

Use the full path format `Folder/Note Title` when multiple notes share the same name.

2

Why is the first search slow?

Local embeddings download the model on first use (~200 MB). Subsequent searches run at normal speed.

3

How do I enable write operations when "READONLY_MODE is enabled"?

Set `READONLY_MODE=false` in your `.env` file.

4

Why are some notes missing from search results?

Run `index-notes` to update the search index. Use `mode: full` if incremental indexing misses changes.

5

Why do I see JXA errors?

Ensure Apple Notes is running and contains at least one note. Grant automation permissions when prompted by macOS.

Comments

More Memory & Knowledge MCP servers

Leviathan Systems Public Content MCP

Leviathan Systems

Search published GPU deployment, rack integration and structured cabling resources; read canonical documents and Leviathan Systems company service scope. Anonymous, read-only Streamable HTTP MCP. No credentials required.

Orcha

westonhancock

Orcha is a unified context layer for AI tools and agents. It stores and indexes and exposes organizational, team, or individual knowledge. Files, structured databases, and connected sources live in one workspace, and age

M1K3

Round-Tower

Local AI agent for your Mac with a built-in MCP server: 18 tools for your notes and PDFs, a temporal memory graph, an on-device LLM and a neural voice. No account, no telemetry. No data centers required.

7

Azquo

Azquo Holdings Ltd

Exact, shared memory for AI agents: a hierarchical database where totals always add up, every write is attributed to the agent and person behind it, and any figure traces back to its source file. Agents create databases,

Neither MCP

stonianua

Project context your AI can query through MCP — with source evidence.

Advertise