About nostalgiaui
nostalgiaui is an MCP server that provides AI coding agents with design-era tokens, palettes, component source, and contrast checks. It helps agents render interfaces using concrete design data instead of guessing.
Key features
- 01List design eras and palettes
- 02Retrieve design tokens
- 03Get component source with imports and CSS
- 04Import VS Code themes
- 05Check color contrast
Use cases
- 01Building a settings page in a chosen design era
- 02Applying a palette to interface components
- 03Checking contrast while creating a UI
MCP support
The MCP server exposes tools to list eras and palettes, retrieve tokens and components, import VS Code themes, and check contrast for MCP clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
6Saved tool list · updated 3d ago
This tool takes no parameters.
Details
From the project README@nostalgiaui/mcp
An MCP server that gives AI coding agents NostalgiaUI's eras, palettes, component source and contrast checks, so an agent asked for a settings page in Frutiger Aero with the Nord palette can get the real tokens rather than guess.
Tools: list_eras, list_palettes, get_tokens, get_component,
import_vscode_theme, check_contrast.
Claude Code
claude mcp add --transport stdio nostalgiaui -- npx -y @nostalgiaui/mcp
Claude Desktop
In claude_desktop_config.json:
{
"mcpServers": {
"nostalgiaui": {
"command": "npx",
"args": ["-y", "@nostalgiaui/mcp"]
}
}
}
get_component returns more than source: the import lines, the era-specific
CSS, and notes naming what is easy to get wrong, such as rendering outside
NostalgiaRoot. Those notes correspond to bugs that were actually hit while
building the library.
Full documentation at nostalgiaui.sylvester.works. MIT, copyright Josh Sylvester and Sylvester Works LLC.
MCP Registry
Listed as io.github.sylvesterworks/nostalgiaui. The listing is
server.json in this package and is published by the release workflow after
each npm publish, authenticated through GitHub OIDC; nothing is done by hand.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.