What is the note structure supported by MCP Notes Server?
Notes are stored as JSON files with fields for `category`, `summary`, `tags` (each containing `tag`, `summary`, and `messages` with `timestamp` and `message`).
@rwelgosh
基本情報
概要はまだありません
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"mcp-notes-server": {
"type": "http",
"url": "http://localhost:8000"
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
上のボタンでサーバーのエンドポイントに接続し、ツール一覧を取得できます。
MCP Notes Server is a simple MCP (Message Coordination Protocol) server that provides programmatic access to notes stored in the ~/DocumentationGenerator/notes/ directory. It is intended for developers and applications that need to list, retrieve, and search note files via an HTTP MCP interface.
To use it, set up a Python virtual environment (Python 3.7+), install dependencies with pip install -r requirements.txt, then start the server by running python notes.py. The server listens on http://0.0.0.0:8000. Clients connect via MCP client libraries and call commands such as list_notes(), get_note(note_name), and search(query, note_name=None).
Notes are stored as JSON files with fields for `category`, `summary`, `tags` (each containing `tag`, `summary`, and `messages` with `timestamp` and `message`).
The server provides three commands: `list_notes()`, `get_note(note_name)`, and `search(query, note_name=None)`.
You need Python 3.7+ and the packages listed in `requirements.txt`. A virtual environment is recommended.
Notes are stored in the `~/DocumentationGenerator/notes/` directory as JSON files.
Clients connect via MCP client libraries (e.g., `MCPClient`) to the HTTP endpoint at `http://localhost:8000` and call the available commands.

Local-first MCP server that snapshots your project's working state into one context object. Open-core, privacy-first.
Project context your AI can query through MCP — with source evidence.

Ask your Takibi Base collections anything; get answers with cited passages and a support score.
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 162 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

AI agents start every session with amnesia — you re-explain the project, repeat your preferences, and correct the same mistakes over and over. PLUR gives them a memory that persists. Your agent's corrections, preference
コメント