Awesome MCPKnowledge & Memory

sirmews/apple-notes-mcp

⭐ 131 Python added to this list on 2025-05-06 repository created 2024-11-30

apple-notes-mcp is a Python Model Context Protocol server that reads the local Apple Notes database on macOS and exposes its contents to Claude Desktop, so an assistant can search and quote notes the user has written over the years. It works by reading the Apple Notes SQLite database directly rather than driving the Notes application, which is why it needs Full Disk Access granted to the server process; the README explains that the database is buried deep in the macOS file system and mentions an AppleScript-based approach as possible future work if writing is ever added. Three tools are provided. get-all-notes returns every note. read-note returns the full content of one note. search-notes searches across the collection. The README is candid about what is missing: encrypted, password-protected notes are not handled, there is no filtering of pinned notes, cloud sync status is ignored, attachment content is not retrieved, checklist status is not exposed, and notes cannot be created or edited, so the server is effectively read-only despite a resources section that mentions reading and writing. Installation is through uv, either uvx apple-notes-mcp to run it directly or uv pip install apple-notes-mcp, followed by an entry in claude_desktop_config.json; the README gives both an unpublished development block that points uv at a project directory and a published block that calls uvx, and notes that the absolute path to uv from which uv may be needed. Development instructions cover uv sync, uv build and uv publish to PyPI, plus debugging through the MCP Inspector, which is recommended because stdio servers are awkward to debug otherwise. The project is MIT licensed. It suits macOS users who keep personal knowledge in Apple Notes and want it searchable from an assistant.

https://github.com/sirmews/apple-notes-mcp

mcpapple-notesmacosnotessqlitepythonpersonal-knowledge

Also in Knowledge & Memory

MemPalace/mempalace

MemPalace is an open-source, local-first AI memory system that stores and retrieves conversation history verbatim using semantic search, supporting pluggable backends like ChromaDB and integrating ...

siyuan-note/siyuan

SiYuan is a privacy-first, self-hosted personal knowledge management system featuring block-level referencing, Markdown WYSIWYG editing, and support for the Model Context Protocol (MCP).

topoteretes/cognee

Cognee is an open-source project that provides scalable and modular memory capabilities for AI agents using ECL pipelines, enabling efficient management and retrieval of past interactions and diverse data types.

vectorize-io/hindsight

Hindsight is an agent memory system designed to create smarter, learning AI agents by moving beyond simple conversation history recall to encompass a biomimetic storage architecture for long-term m...

screenpipe/screenpipe

Screenpipe is a local-first, AI-powered memory tool that records computer activity (screen, audio, accessibility tree) to provide a searchable, automated context for personal AI agents and users, i...

Olow304/memvid

Memvid is a video-based AI memory library that stores millions of text chunks in MP4 files with ultra-fast semantic search, eliminating the need for traditional databases and enabling portable, efficient AI memory management.

EverMind-AI/EverOS

EverOS is an open-source Python framework for self-evolving, portable, long-term memory for AI agents, supporting multimodal ingestion and local-first persistence with Markdown as the source of truth.

MemTensor/MemOS

MemOS is a Memory Operating System for LLMs and AI agents that unifies long-term memory management, offering a single API for structured, multi-modal memory with enterprise-grade optimizations, sig...