What does this server do?
It provides a simple notes system: you can list existing notes and create new ones via the `create_note` tool. Notes are stored in the server’s state and accessible through `note://` URIs.
@handfuloflight
基本情報
概要はまだありません
Create new text notes
It is a TypeScript-based MCP (Model Context Protocol) server that implements a simple notes system. It demonstrates core MCP concepts by providing resources for notes and tools to create them. This server is intended for developers working with MCP and Claude Desktop.
Install dependencies with npm install, then build with npm run build. Add the server configuration to Claude Desktop’s claude_desktop_config.json (on MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json; on Windows: %APPDATA%/Claude/claude_desktop_config.json). The server runs via stdio using the built index.js.
note:// URIs.create_note tool to create new text notes.It provides a simple notes system: you can list existing notes and create new ones via the `create_note` tool. Notes are stored in the server’s state and accessible through `note://` URIs.
No. All notes are stored in the server’s in‑memory state. There is no persistence across restarts.
Run `npm build` then `npm start`? Actually the README shows `npm run build` to build, then you run the compiled `index.js`. For auto‑rebuild use `npm run watch`. Debugging is possible with the MCP Inspector (`npm run inspector`).
It communicates over stdio (standard input/output) as a standard MCP server.
The server does not implement any authentication—it runs locally and is intended for personal desktop use with Claude Desktop.
PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct
Open-source MCP to use Blender with any LLM

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code
🚀 The fast, Pythonic way to build MCP servers and clients.
Hindsight: Agent Memory That Learns
コメント