artscii
ASCII art & kaomoji for AI agents, CLI tools, and chatbots.
README
artscii
ASCII art & kaomoji for AI agents, CLI tools, and chatbots. 101 built-in arts + 100 kaomoji, searchable via MCP or REST API.
.::-::. .:-::. --- apple (16w) ---
.=#%@@@@@%#=: .=*%@@@@@%#+: +:
-%@@@@@@@@@@@%*+%@@@@@@@@@@@%+ :--:#*.--:
.%@@@@@@@@@@@@@@@@@@@@@@@@@@@@@- -#@@@@#%@@@@%=
-@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@* :@@@%****+#%@@@:
.%@@@@@@@@@@@@@@@@@@@@@@@@@@@@@= -@%%%+*@@+*@%%@-
=@@@@@@@@@@@@@@@@@@@@@@@@@@@@* *@@%+*+#=#%@@#
-#@@@@@@@@@@@@@@@@@@@@@@@@%= +%@@@#@@@@%+
=%@@@@@@@@@@@@@@@@@@@@%*. .-+**=*+=.
=#@@@@@@@@@@@@@@@@%+.
=#@@@@@@@@@@@@%+. ʕ•ᴥ•ʔ (◕‿◕) (╯°□°)╯︵ ┻━┻
-#@@@@@@@@%+.
-#@@@@%=.
-*#=
Use Cases
Give your CLI personality. Replace boring spinners with ASCII art loading screens, success badges, or error illustrations.
import { execSync } from 'child_process';
// npx artscii runs the MCP server — or just fetch from the REST API:
const art = await fetch('http://localhost:3001/art/trophy/raw').then(r => r.text());
console.log(art); // 16w trophy on build success
Make chatbots expressive. Discord/Slack bots can react with kaomoji that match the mood — no custom emoji uploads needed.
const res = await fetch('http://localhost:3001/kaomoji?q=celebrate');
const [first] = await res.json();
bot.reply(`Deploy complete! ${first.text}`); // Deploy complete! (ノ◕ヮ◕)ノ*:・゚✧
Add visuals to AI agents without wasting tokens. A 16w art is only 8 lines — far cheaper than describing an image in natural language.
{
"mcpServers": {
"artscii": { "command": "npx", "args": ["-y", "artscii"] }
}
}
"Show me a cat" → MCP
search("cat")→ returns 32w cat silhouette +ฅ•ω•ฅkaomoji
Install
Claude Code — one command:
claude mcp add artscii -- npx -y artscii
Claude Desktop — add to claude_desktop_config.json:
{ "mcpServers": { "artscii": { "command": "npx", "args": ["-y", "artscii"] } } }
Cursor — add to .cursor/mcp.json:
{ "mcpServers": { "artscii": { "command": "npx", "args": ["-y", "artscii"] } } }
VS Code — search @mcp artscii in Extensions panel, or add to settings.json:
{ "mcp": { "servers": { "artscii": { "command": "npx", "args": ["-y", "artscii"] } } } }
REST API — npx artscii starts the server on :3001
MCP Tools
| Tool | Parameters | Description |
|---|---|---|
search |
query, type? |
Search art + kaomoji. type: "art", "kaomoji", or "all" |
kaomoji |
query?, category? |
Get kaomoji by emotion. Omit for random |
get |
id |
Get art by ID |
random |
— | Random art |
list |
— | List all arts |
categories |
— | List categories |
submit |
name, category, tags, size?, art |
Submit new art |
convert |
url?, base64?, size?, ... |
Convert image to ASCII |
delete |
id |
Delete user-submitted art |
REST API
| Endpoint | Description |
|---|---|
GET /search?q={query}&type=art|kaomoji |
Unified search |
GET /art/:id |
Art by ID (JSON) |
GET /art/:id/raw |
Raw ASCII text |
GET /random |
Random art |
GET /categories |
List categories |
GET /categories/:name |
Arts in category |
GET /list |
All arts metadata |
POST /art |
Submit art |
POST /convert |
Image → ASCII |
DELETE /art/:id |
Delete user art |
GET /kaomoji?q={query} |
Search kaomoji |
GET /kaomoji/random |
Random kaomoji |
GET /kaomoji/categories |
Kaomoji categories |
GET /kaomoji/categories/:name |
Kaomoji by category |
Submit Art
curl -X POST http://localhost:3001/art \
-H 'Content-Type: application/json' \
-d '{"name":"Robot","category":"objects","tags":["robot","tech"],"size":16,"art":" [o_o]\n /| |\\\n d b"}'
Convert Image
curl -X POST http://localhost:3001/convert \
-H 'Content-Type: application/json' \
-d '{"url":"https://example.com/icon.png","size":16}'
| Field | Type | Default | Description |
|---|---|---|---|
url / base64 |
string | — | Image source (one required) |
size |
16 / 32 / 64 | 16 | Size tier |
invert |
boolean | false | Invert brightness |
contrast |
boolean | true | Auto-contrast |
gamma |
number | 1.0 | Gamma correction |
save |
object | — | { name, category, tags } to persist |
Size Tiers
Each art is stored at its minimum identifiable size.
| Tier | Dimensions | For |
|---|---|---|
| 16w | 16 x 8 | Icons, symbols, simple shapes |
| 32w | 32 x 16 | Animal silhouettes, emoji |
| 64w | 64 x 32 | Detailed scenes (rare) |
Kaomoji
90 curated entries across 22 categories. Source: kao.moji (MIT).
| Category | Examples |
|---|---|
| happy | (◕‿◕) ◉‿◉ (≧◡≦) |
| sad | (ಥ﹏ಥ) ╥﹏╥ (;﹏;) |
| angry | ಠ_ಠ (¬_¬) 눈_눈 |
| love | ♡^▽^♡ (•ө•)♡ ✿♥‿♥✿ |
| confused | ¯\_(ツ)_/¯ ◔_◔ (・・?) |
| animals | ʕ•ᴥ•ʔ ฅ•ω•ฅ (•ㅅ•) |
| table-flip | (╯°□°)╯︵ ┻━┻ ┬─┬ノ(ಠ_ಠノ) |
| + 15 more | excited, greeting, celebrate, hug, surprised, sleepy, nervous, wink, magic, laughing, determined, eating, dancing, hopeful, jealous |
License
MIT. Art icons from game-icons.net (CC BY 3.0, Lorc & Delapouite).
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.