MCP HubMCP Hub
modelcontextprotocol

everart

by: modelcontextprotocol

Image generation server for Claude Desktop using EverArt's API.

0created 19/11/2024
Visit
Image
API

📌Overview

Purpose: To provide an image generation server that integrates with Claude Desktop using EverArt's API.

Overview: The EverArt MCP Server facilitates the generation of high-quality images through various model options, allowing users to create custom images based on textual prompts directly from their applications. This server can be configured to run using Docker or NPX for seamless deployment.

Key Features:

  • Image Generation: Generates images based on user-defined prompts with multiple model options to choose from, enabling varying quality and styles according to user needs.

  • Custom Configuration: Supports flexible deployment methods (Docker and NPX), allowing users to easily set up the server with their API key and integrate it into their existing workflows.


EverArt MCP Server

Image generation server for Claude Desktop using EverArt's API.

Installation

npm install
export EVERART_API_KEY=your_key_here

Configuration

Docker

{
  "mcpServers": {
    "everart": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "-e", "EVERART_API_KEY", "mcp/everart"],
      "env": {
        "EVERART_API_KEY": "your_key_here"
      }
    }
  }
}

NPX

{
  "mcpServers": {
    "everart": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-everart"],
      "env": {
        "EVERART_API_KEY": "your_key_here"
      }
    }
  }
}

Image Generation

generate_image

Generates images with multiple model options.

Parameters

{
  prompt: string,       // Image description
  model?: string,       // Model ID (default: "207910310772879360")
  image_count?: number  // Number of images (default: 1)
}

Available Models

  • 5000: FLUX1.1 (standard)
  • 9000: FLUX1.1-ultra
  • 6000: SD3.5
  • 7000: Recraft-Real
  • 8000: Recraft-Vector

All images are generated at 1024x1024.

Sample Usage

const result = await client.callTool({
  name: "generate_image",
  arguments: {
    prompt: "A cat sitting elegantly",
    model: "7000",
    image_count: 1
  }
});

Response Format

Image generated successfully!
The image has been opened in your default browser.

Generation details:
- Model: 7000
- Prompt: "A cat sitting elegantly"

Building with Docker

docker build -t mcp/everart -f src/everart/Dockerfile .