@frankunderwood-w
基本情報
MCP Server that provides kaomoji between conversations for AI Agents
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": {
"kaomoji_mcp_server": {
"command": "node",
"args": [
"build/index.js",
"#",
"starts",
"the",
"stdio",
"server"
]
}
}
}gentle fix, formal context → `(^-^)`
regular task done → `(^o^)/`
major breakthrough → `\(^∀^)/`
search returned no results
unexpected error occurred
user expressed unhappiness
Kaomoji is a Model Context Protocol (MCP) server that gives AI agents expressive, CLI-safe kaomoji (ASCII emoticons) for key interaction moments: thinking, celebrating, and apologizing. All kaomoji use only ASCII/half‑width characters, ensuring they render correctly in any terminal, IDE panel, or chat interface. It is built for developers using MCP‑compatible agents (e.g., Claude Desktop, Cursor, VS Code + GitHub Copilot, Windsurf, Zed, Continue.dev, Cline).
Install Kaomoji via npm (npm install -g kaomoji-mcp) or use it directly with npx kaomoji-mcp. Configure it as an MCP server in your client's settings (e.g., claude_desktop_config.json, mcp.json, settings.json) using the stdio transport. Once connected, the agent will automatically know how to call the three tools at the appropriate moments; you can also load the react_with_kaomoji prompt to provide full behavior guidelines.
thinking_kaomoji, celebrate_kaomoji, apologize_kaomojireact_with_kaomoji prompt that teaches agents when and how to use each toolkaomoji://catalog resource exposing the complete kaomoji database (75+ entries) as JSONKaomoji provides three tools: `thinking_kaomoji` (called before each sub‑task, accepts a `phase` description), `celebrate_kaomoji` (called after success, with `intensity` parameter), and `apologize_kaomoji` (called on failure, with `reason` parameter).
Kaomoji requires **Node.js ≥ 20**. It runs as a stdio MCP server and can be invoked via `npx` without installation, globally installed with npm, or cloned from GitHub and built locally.
No. Once the server is referenced in your MCP client’s configuration (using stdio transport), the agent will automatically receive the server instructions on connection. Optionally, you can add the `react_with_kaomoji` prompt to your system prompt.
Yes. All kaomoji in the database are CLI‑safe—they contain only ASCII and half‑width characters, so they render without issues in any terminal, IDE panel, or chat interface.
You can run Kaomoji via `npx kaomoji-mcp` (no install needed), install globally with npm, clone the repository and build locally, or deploy on Smithery using their CLI (`npx @smithery/cli install kaomoji-mcp`). All deployments use stdio transport.
不止于 CSS
Request dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3
A free remote MCP server for The Living Bread. Bible passages read word for word from a stored public domain text with an evidence label, keyword search and cross references, real churches, gatherings and prayer groups w
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
See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.
コメント