Popmelt MCP Server

@MCP-Mirror

Repository

Basic information

About Popmelt MCP Server

Mirror of

#mcp-server#popmelt#talent-ai

Popmelt MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "popmelt-mcp-server": {
      "command": "node",
      "args": [
        "dist/server.js"
      ]
    }
  }
}

Popmelt MCP Server tools

Generate CSS for a component based on a talent profile

Generate CSS for a complete component library

Perform a read-only query on talent metadata

Analyze compatibility between different talent styles

Overview

What is Popmelt MCP Server?

The Popmelt MCP Server is an MCP (Model Context Protocol) server that exposes Talent AI profiles and styling capabilities to LLMs and applications. It connects directly to Popmelt's PostgreSQL database to retrieve detailed talent profiles with structured metadata and weighted styling attributes, enabling dynamic UI component styling.

How to use Popmelt MCP Server?

Install Node.js 18+ and PostgreSQL, clone the repository, install dependencies, configure the .env file with database credentials, run node scripts/setup-db.js to initialize the database, then build with npm run build. Run in stdio mode with npm start or in HTTP/SSE mode with npm run start:http. Use an MCP client to list resources, read talent profiles, generate CSS, or invoke tools like generate-css.

Key features of Popmelt MCP Server

Talent AI Profile Access: retrieve complete aesthetic and design data
CSS Styling Generation: generate CSS rules from stored metadata
Dynamic UI Component Styling: integrate talent-driven design into components
Database Integration: direct PostgreSQL connection for talent profiles
Multiple Transport Options: stdio for CLI or HTTP with SSE for remote
Prompt templates for style recommendations and talent descriptions

Use cases of Popmelt MCP Server

Generate custom CSS for UI components based on a talent’s aesthetic profile
Compare style compatibility between two talent profiles
List all available talent profiles and query by metadata filters
Create an LLM prompt to style a component with specific requirements
Build a complete component library CSS from a single talent profile

Frequently asked questions

What dependencies does the server require?

Node.js 18 or higher and a PostgreSQL database.

What transport options are available?

Stdio transport for command-line tools and direct integration, and HTTP server with SSE for remote access.

What data is stored in the database?

A `talents` table with fields `id`, `name`, `description`, timestamps, and a JSONB `metadata` column containing aesthetic characteristics, design attributes, color palette, and typography.

How do I set up the database?

Copy `.env.example` to `.env` and fill in your PostgreSQL credentials, then run `node scripts/setup-db.js` to execute the schema SQL.

What tools does the server expose?

Four tools: `generate-css` (generate CSS for a component), `generate-component-library` (full library CSS), `query-talents` (filter talent metadata), and `analyze-style-compatibility` (compare two talents).

Comments

More Developer Tools MCP servers

DocuWriter.ai

DocuWriter is an AI-powered platform for creating, updating and managing complete, structured documentation for entire codebases. Teams can connect repositories and generate documentation covering architecture, modules,

Routebase

Routebase keeps your API's design, docs, contract tests, mocks and monitoring in one living OpenAPI spec so they can't drift apart. Agents work on that same source of truth, under your team's permissions.

LastPing

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci

Mobbin

Mobbin MCP connects your AI agents to 600,000+ real product screens, so what they build starts with what already works.

Modelglass

Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott