Kaomoji

by frankunderwood-w

190 downloads

Not rated

GitHub

About

MCP Server that provides kaomoji between conversations for AI Agents

Details

Author: frankunderwood-w
Downloads: 190
Categories: Communication, AI, Other

- Three dedicated tools: thinking_kaomoji, celebrate_kaomoji, apologize_kaomoji
- A react_with_kaomoji prompt that teaches agents when and how to use each tool
- A kaomoji://catalog resource exposing the complete kaomoji database (75+ entries) as JSON
- All kaomoji are CLI‑safe (no full‑width or decorative Unicode characters)
- Works with many popular MCP clients: Claude Desktop, Claude Code, Cursor, VS Code + Copilot, Windsurf, Zed, Continue.dev, Cline, Smithery

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below

Plugin Name Kaomoji

Command (node, npx, python, etc.)

Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "kaomoji": {
            "kaomoji_mcp_server": {
                "command": "node",
                "args": [
                    "build/index.js",
                    "#",
                    "starts",
                    "the",
                    "stdio",
                    "server"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "kaomoji": {
            "kaomoji_mcp_server": {
                "command": "node",
                "args": [
                    "build/index.js",
                    "#",
                    "starts",
                    "the",
                    "stdio",
                    "server"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "kaomoji": {
            "kaomoji_mcp_server": {
                "command": "node",
                "args": [
                    "build/index.js",
                    "#",
                    "starts",
                    "the",
                    "stdio",
                    "server"
                ]
            }
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "kaomoji": {
            "kaomoji_mcp_server": {
                "command": "node",
                "args": [
                    "build/index.js",
                    "#",
                    "starts",
                    "the",
                    "stdio",
                    "server"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "kaomoji": {
            "kaomoji_mcp_server": {
                "command": "node",
                "args": [
                    "build/index.js",
                    "#",
                    "starts",
                    "the",
                    "stdio",
                    "server"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "kaomoji": {
            "kaomoji_mcp_server": {
                "command": "node",
                "args": [
                    "build/index.js",
                    "#",
                    "starts",
                    "the",
                    "stdio",
                    "server"
                ]
            }
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "kaomoji": {
            "kaomoji_mcp_server": {
                "command": "node",
                "args": [
                    "build/index.js",
                    "#",
                    "starts",
                    "the",
                    "stdio",
                    "server"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "kaomoji": {
            "kaomoji_mcp_server": {
                "command": "node",
                "args": [
                    "build/index.js",
                    "#",
                    "starts",
                    "the",
                    "stdio",
                    "server"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "kaomoji": {
            "kaomoji_mcp_server": {
                "command": "node",
                "args": [
                    "build/index.js",
                    "#",
                    "starts",
                    "the",
                    "stdio",
                    "server"
                ]
            }
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "kaomoji": {
            "kaomoji_mcp_server": {
                "command": "node",
                "args": [
                    "build/index.js",
                    "#",
                    "starts",
                    "the",
                    "stdio",
                    "server"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "kaomoji": {
            "kaomoji_mcp_server": {
                "command": "node",
                "args": [
                    "build/index.js",
                    "#",
                    "starts",
                    "the",
                    "stdio",
                    "server"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "kaomoji": {
            "kaomoji_mcp_server": {
                "command": "node",
                "args": [
                    "build/index.js",
                    "#",
                    "starts",
                    "the",
                    "stdio",
                    "server"
                ]
            }
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "kaomoji": {
            "kaomoji_mcp_server": {
                "command": "node",
                "args": [
                    "build/index.js",
                    "#",
                    "starts",
                    "the",
                    "stdio",
                    "server"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "kaomoji": {
            "kaomoji_mcp_server": {
                "command": "node",
                "args": [
                    "build/index.js",
                    "#",
                    "starts",
                    "the",
                    "stdio",
                    "server"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "kaomoji": {
            "kaomoji_mcp_server": {
                "command": "node",
                "args": [
                    "build/index.js",
                    "#",
                    "starts",
                    "the",
                    "stdio",
                    "server"
                ]
            }
        }
    }
}

From the repository

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.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "kaomoji": {
            "kaomoji_mcp_server": {
                "command": "node",
                "args": [
                    "build/index.js",
                    "#",
                    "starts",
                    "the",
                    "stdio",
                    "server"
                ]
            }
        }
    }
}

McpServers

{
    "kaomoji_mcp_server": {
        "command": "node",
        "args": [
            "build/index.js",
            "#",
            "starts",
            "the",
            "stdio",
            "server"
        ]
    }
}

kaomoji-mcp

> CLI-safe kaomoji for AI Agents at key interaction points

A Model Context Protocol (MCP) server that gives AI agents expressive kaomoji (ASCII emoticons) at key moments — thinking, celebrating, and apologizing. All kaomoji are CLI-safe: no full-width characters, no decorative Unicode, no rendering surprises in any terminal. ``


Searching for auth middleware
(..)

All tests passed! (^o^)/



---

Table of Contents


- Why kaomoji-mcp?
- Tools, Prompts & Resources
- Installation
- Quickstart
- Configuration by Client
  - Claude Desktop
  - Claude Code (CLI)
  - Cursor
  - VS Code + GitHub Copilot
  - Windsurf
  - Zed
  - Continue.dev
  - Cline / Roo Cline
  - Smithery
- Development
- Running Tests

---

Why kaomoji-mcp?


Modern AI agents work through multiple sub-tasks before delivering an answer. Without visual indicators, the user sees nothing until the final response. kaomoji-mcp solves this by asking the agent to:

- Show a thinking kaomoji before each sub-task so the user can follow progress in real time
- Show a celebration kaomoji when a task completes successfully
- Show an apology kaomoji when results are not found or an error occurs

Because all characters are ASCII / half-width compatible, they render correctly in every terminal, IDE panel, and chat interface.

---

Tools, Prompts & Resources


Tools


| Tool | When to call | Key parameter |
|------|-------------|---------------|
|

thinking_kaomoji | Before each sub-task or reasoning phase | phase (string, max 80 chars); optional mcp_server

|
|

celebrate_kaomoji | After a task completes successfully | intensity: "subtle" / "moderate" / "intense"

|
|

apologize_kaomoji | On no-results, error, or user dissatisfaction | reason: "not_found" / "error" / "dissatisfied"

thinking_kaomoji — Progress indicator. Call once per sub-task. Accepts an optional mcp_server

 parameter to show which external MCP server is being delegated to:


Reading project files [filesystem]
(._.)

celebrate_kaomoji

 — Completion signal. Choose intensity to match the moment:
-

subtle — gentle fix, formal context → (^-^)

moderate — regular task done → (^o^)/

intense — major breakthrough → \(^∀^)/

apologize_kaomoji — Failure signal. The reason

 field classifies the situation:
-

not_found

 — search returned no results
-

error

 — unexpected error occurred
-

dissatisfied

 — user expressed unhappiness

Prompt


| Prompt | Description |
|--------|-------------|
|

react_with_kaomoji

 | Full behavior guide — load this prompt to give the agent detailed rules about when and how to use all three tools |

Resource


| URI | MIME | Description |
|-----|------|-------------|
|

kaomoji://catalog | application/json

 | Full kaomoji database with all scenes, intensities, states, reasons, fallback strings, and bilingual tags |

---

Installation


Requirements


- Node.js ≥ 20

Option A — npx (no install, always latest)


No installation needed. Just reference the package in your MCP client config (see below) and the agent runtime will fetch it automatically.


npx kaomoji-mcp



Option B — Global install

bash
npm install -g kaomoji-mcp
kaomoji-mcp   # starts the stdio server



Option C — Local project clone

bash
git clone https://github.com/frankunderwood-w/kaomoji_mcp_server.git
cd kaomoji-mcp
npm install
npm run build
node build/index.js   # starts the stdio server



Option D — Local project by npm

bash
mkdir my-project && cd my-project
npm init -y
npm install kaomoji-mcp



---

Quickstart


Once configured, your MCP-compatible agent will automatically receive the server instructions on connection and will know to call the tools at the right moments. You can also explicitly load the behavior guide by requesting the

react_with_kaomoji

 prompt in your system prompt.

---

Configuration by Client


All configurations below launch the server over stdio transport. Replace

node /absolute/path/to/build/index.js with npx kaomoji-mcp

 if you prefer to use the npm package directly.

---

Claude Desktop


Config file location:
- macOS:

~/Library/Application Support/Claude/claude_desktop_config.json


- Windows:

%APPDATA%\Claude\claude_desktop_config.json

json
{
  "mcpServers": {
    "kaomoji": {
      "command": "npx",
      "args": ["-y", "kaomoji-mcp"]
    }
  }
}



Or, if you cloned the repo locally:

json
{
  "mcpServers": {
    "kaomoji": {
      "command": "node",
      "args": ["/absolute/path/to/kaomoji-mcp/build/index.js"]
    }
  }
}



Restart Claude Desktop after saving. The server should appear under Settings → Developer → MCP Servers.

---

Claude Code (CLI)


Add the server to your project or user configuration:

``bash

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

From the repository

Claude Desktop / Cursor

McpServers

kaomoji-mcp

Table of Contents

Why kaomoji-mcp?

Tools, Prompts & Resources

Tools

Prompt

Resource

Installation

Requirements

Option A — npx (no install, always latest)

Option B — Global install

Option C — Local project clone

Option D — Local project by npm

Quickstart

Configuration by Client

Claude Desktop

Claude Code (CLI)

Install

More like this

Sequential Thinking

Slack

Filesystem

EverArt

Google Drive

Context 7