heybeauty MCP Server

Use This MCP server To

List and access virtual clothes with metadata and images Submit virtual try-on tasks using user and cloth images Query status and results of virtual try-on tasks Integrate virtual try-on into fashion e-commerce platforms Enable real-time virtual fitting room experiences Automate virtual try-on workflows in MCP clients

README

HeyBeauty MCP Server

HeyBeauty Virtual TryOn

This is a TypeScript-based MCP server that implements virtual tryon using HeyBeauty API. It demonstrates core MCP concepts by providing:

Resources representing clothes with URIs and metadata
Tools for submit tryon task and query task info.
Prompts for tryon cloth.

Quick Start

apply for HeyBeauty API Key
add the server config to MCP Client config file

{
  "mcpServers": {
    "heybeauty-mcp": {
      "command": "npx",
      "args": ["-y", "heybeauty-mcp"],
      "env": {
        "HEYBEAUTY_API_KEY": "your_heybeauty_api_key"
      }
    }
  }
}

Resources

List and access clothes via cloth:// URIs
Each cloth has a id, name, description, image url and metadata
Plain text mime type for simple content access

Tools

submit_tryon_task - Submit a tryon task
- Takes user image url, cloth image url, cloth id and cloth description as required parameters
- Stores tryon task in server state
query_tryon_task - Query a tryon task
- Takes task id as required parameter
- Returns tryon task info

Prompts

tryon_cloth - Tryon cloth
- Takes user image url, cloth image url, cloth id and cloth description as required parameters
- Returns structured prompt for LLM tryon

Resources

cloth:// - URI for clothes
- Each cloth has a id, name, description, image url and metadata

Development

Install dependencies:

npm install

Build the server:

npm run build

For development with auto-rebuild:

npm run watch

Installation

To use with Claude Desktop, add the server config:

On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "heybeauty-mcp": {
      "command": "node",
      "args": ["/path/to/heybeauty-mcp/build/index.js"]
    },
    "env": {
      "HEYBEAUTY_API_KEY": "your_heybeauty_api_key"
    }
  }
}

Follow this document to get HeyBeauty API Key.

Debugging

Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:

npm run inspector

The Inspector will provide a URL to access debugging tools in your browser.

heybeauty-mcp FAQ

How do I configure the HeyBeauty MCP server with my API key?

Obtain a HeyBeauty API key from their website and add it to the MCP client config under the heybeauty-mcp server environment variables.

What resources does the HeyBeauty MCP server expose?

It exposes clothes as resources with URIs, including metadata like id, name, description, and image URLs.

What tools are available in the HeyBeauty MCP server?

Tools include submit_tryon_task to start a try-on and query_task_info to check task status.

Can I use this server with different LLM providers?

Yes, it is provider-agnostic and works with OpenAI, Claude, Gemini, and others.

What programming language is the HeyBeauty MCP server built with?

It is implemented in TypeScript for easy integration and extensibility.

How does the server handle virtual try-on tasks?

It submits tasks to the HeyBeauty API using user and cloth images, then provides task status and results.

Is there a quick start guide for integrating this server?

Yes, the GitHub readme provides steps to apply for an API key and configure the MCP client.

What MIME types are supported for resource content?

Plain text MIME type is supported for simple content access.