The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the Ascii Art listing page.
ascii-art-mcp is a Model Context Protocol (MCP) server built with Node.js and TypeScript that exposes tools for retrieving ASCII and Unicode art from a local database.
The server communicates using stdio transport, making it compatible with MCP clients such as:
Just drop this link into any MCP-compatible AI chat:
"Run this MCP"
The AI will clone the repo, build it, and run it automatically. No setup needed on your end.
The package is available on npm:
https://www.npmjs.com/package/ascii-art-mcp
Install locally:
Or run directly:
This server is also published in the official Model Context Protocol Registry:
https://registry.modelcontextprotocol.io/?q=ascii-art
Server name:
This allows MCP-compatible tools to discover and install it automatically.
Development mode:
Build + production run:
The server uses stdio transport and loads its data from:
located in the repository root.
Finds an art entry by exact nombre or by an exact value in aliases.
| Field | Type | Required |
|---|---|---|
| query | string | yes |
Returns the entry's art field as plain text.
Searches entries by categoria, tags, or both.
| Field | Type | Required |
|---|---|---|
| categoria | string | optional |
| tag | string | optional |
At least one filter is required.
Returns matching entries' art fields combined as text output.
Returns a random entry from the database.
| Field | Type | Required |
|---|---|---|
| tipo | ascii | unicode | required |
Returns the selected entry's art field as plain text.
Lists all unique categories present in the database.
None
Category names as newline-separated text.
Entries in db.json follow the AsciiArtEntry TypeScript interface:
Each entry contains metadata such as:
A simple integration test was used to verify MCP communication using JSON-RPC over stdio.
Example test script (test.mjs):
db.json)This project demonstrates how to build a simple MCP tool server that:
MIT