#note-taking

Strata is a self hosted AI memory server. Your AI remembers everything across every session, on your own hardware. Key features: . Semantic search (find memories by meaning, not keywords) . Per-agent API keys with granular permissions . 3D constellation viewer with live agent activity . File vault (attach real documents to memories) . CSV audit log (full transparency on every agent action) . Pre-Strata history import (your memory doesn't start at install day) . Global MCP kill switch (emergency brake, only a human can undo) . Automatic deduplication . 10 structured thought types . Backend using PostgreSQL . Runs on a Raspberry Pi Always on, always local, always yours.

Give your AI long-term memory. Hjarni is a note-taking app with a built-in MCP server. Claude and ChatGPT can search, read, create, and organize your notes. Markdown, folders, tags, and custom AI instructions per folder.

Official flomo MCP server. Connect AI assistants to your flomo notes — search, create, edit notes and manage tags via Model Context Protocol.

Two-way markdown workspace for Claude. Version history, line-by-line diffs, attribution tracking, and revert on every edit. Claude reads your project context and writes back. Notes, logs, roadmaps — versioned like code. EU-hosted. Export everything. No lock-in.

Enhanced MCP server for Capacities, the knowledge management app. Features include listing spaces, searching content with full-text and title modes, retrieving complete object content by ID, saving weblinks with metadata and tags, and adding content to daily notes. Fork of the original with updated fastmcp for MCP SDK compatibility and tested Windows support.

Sticky Note MCP Server is a minimal yet powerful implementation of the **Model Context Protocol (MCP)** built with **FastMCP** in Python. It lets agents and users create, manage, and summarize sticky notes directly through MCP tools and resources. ### ✨ Features - 📝 Create, list, update, and delete notes - 🏷️ Add tags and pinned/archived status - 🔍 Search and filter by keyword or tag - 🧠 Generate AI-based summaries or roadmaps - 🗂️ Built-in resources: - `notes://latest` - `notes://pinned` - `notes://stats` ### 🧰 Tool Endpoints - `add_note(message, tags=None, pinned=False)` - `list_notes(tags=None, pinned=None, archived=None)` - `search_notes(query)` - `update_note(note_id, message=None, pinned=None, archived=None)` - `delete_note(note_id)` - `clear_notes()` ### 🚀 Getting Started 1. Clone the repository: ```bash git clone https://github.com/aynul-abedin/sticky-note-mcp-server cd sticky-note-mcp-server

MCP Server for local notes while playing through Blue Prince

# Notes MCPAn MCP server that connects with your Apple Notes on macOS. 📓 This tool allows you to manage your notes efficiently with simple commands. 🛠️

Let AI agents like ChatGPT & Claude use real-world local/remote tools you approve via browser extension + optional MCP server

A custom server project built using the Model Context Protocol (MCP) in Python. This repository documents my learning, experiments, and development progress.

A Python-based Model Context Protocol (MCP) server using a file‑system backend, offering tools for note taking, file I/O, directory management, search, compression, and metadata retrieval.

MCP Server for taking notes using an LLM client like Claude Desktop.

record notes to flomo

A Model Context Protocol (MCP) server that implements the Zettelkasten knowledge management methodology, allowing you to create, link, explore and synthesize atomic notes through Claude and other MCP-compatible clients.

A memo tool based on MCP protocol that helps developers quickly save and retrieve text information without interrupting their workflow.

Mirror of

a MCP server to record Claude conversation to markdown or Apple Notes

Model Context Protocol (MCP) server designed for LLMs to interact with Obsidian vaults. Provides secure, token-aware tools for seamless knowledge base management through a standardized interface.

A simple note-taking MCP server for recording and managing notes with AI models.