What technology stack does Popmelt MCP Server use?
It uses Node.js, Express.js, fs-extra, body-parser, cors, and Jest with Supertest for testing. The frontend uses HTML, CSS, and JavaScript.
@avantjohn
Basic information
No overview available yet
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Popmelt MCP Server is a Model-Controlled Programming server for Popmelt, a platform that generates dynamic design systems and UI components based on structured Taste Profiles defined in JSON metadata files. It provides a RESTful API, a visual frontend dashboard, and CSS generation from design tokens.
Clone the repository, install dependencies with npm install, and start the server with npm start (or npm run dev for hot reloading). The server runs on port 3000 by default, configurable via the PORT environment variable. Use the API endpoints or open http://localhost:3000 in a browser to access the visual dashboard.
/profiles directoryIt uses Node.js, Express.js, fs-extra, body-parser, cors, and Jest with Supertest for testing. The frontend uses HTML, CSS, and JavaScript.
Profiles contain design tokens such as colors, spacing, typography, borders, and animations. The server automatically converts these tokens into CSS variables (e.g., `--color-background`, `--spacing-medium`).
Endpoints include POST `/api/profiles` (create), GET `/api/profiles` (list all), GET `/api/profiles/:slug` (get one), PUT `/api/profiles/:slug` (update), and DELETE `/api/profiles/:slug` (delete).
Yes, the `POST /api/generate-design-system` endpoint generates CSS for all components defined in a profile.
A health check endpoint is available at `/api/health`.

Read and edit DB Planner database schemas (DBML/SQL), Mermaid diagrams and board layouts from any MCP client. 38 tools, OAuth sign-in, read and write as separate scopes enforced server-side.

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.

Complete, hosted login, teams, billing and feature flags for your SaaS app, set up by your AI assistant: sign-in and SSO, customer teams and roles, plans and usage limits on Stripe, and feature flags. OAuth sign-in, no A

Agent-Native Terminal
Comments