How are notes stored in MCP Notes Server?
Notes are stored in a local `notes_storage.json` file. Each note includes its content, creation timestamp, and last modification timestamp.
@truaxki
基本情報
A Model Context Protocol (MCP) server implementation providing persistent note management created with Python SDK.
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-truaxki": {
"command": "npx",
"args": [
"-y",
"@smithery/cli",
"install",
"notes",
"--client",
"claude"
]
}
}
}Create a new note
Display all stored notes
Modify an existing note
Remove a note
MCP Notes Server is a Model Context Protocol (MCP) server implementation for managing notes with persistent storage. It provides create, read, update, and delete operations, timestamp tracking, note summarization via prompts, and resource-based access using a note:// URI scheme. It is intended for users who need note management integrated into an MCP client.
Install automatically via Smithery (npx -y @smithery/cli install notes --client claude) or manually with Python 3.10+ and the MCP package. Start the server with mcp install src/notes and mcp start Notes, then call tools like add-note, list-all-notes, update-note, and delete-note from an MCP client.
note:// URI schemeNotes are stored in a local `notes_storage.json` file. Each note includes its content, creation timestamp, and last modification timestamp.
It provides four tools: `add-note` to create a note, `list-all-notes` to display all notes, `update-note` to modify an existing note, and `delete-note` to remove a note.
Notes can be accessed using the `note://` URI scheme. Listing resources returns all available notes, and a specific note is read via `note://internal/note_name`.
The server includes a "summarize-notes" prompt that generates both brief and detailed summaries of notes, formatting them for language model input.
It requires Python 3.10 or later and the `MCP` Python package. The server uses no external database – persistence is handled by JSON file storage.
Person-owned, portable AI memory served over MCP. Your knowledge, preferences, and decisions — captured in one assistant, available in all of them.

Sooveryn gives Claude Code a team of AI personas that remembers your project. Soov, the partner and team lead, keeps your decisions and how you work in a lasting memory, and finds them again by words and by meaning, from

The Cloud is the AI-native workspace that gives every AI — Claude, ChatGPT, Gemini, and other Frontier & Free or Local models — shared memory and real agents. Not cloud computing: thecloud.so is one workspace where your

Personal context for every AI: search, read, and write back to your private Markdown library of articles, threads, PDFs, notes, and captured ChatGPT/Claude/Gemini/Grok conversations. Remote server, OAuth 2.1 paste-and-au
Shared, serverless, conflict-free memory for AI agents: a multi-machine drop-in for the MCP memory knowledge graph.
コメント