Navigation
EverArt: AI-Powered Mix & Match Magic - MCP Implementation

EverArt: AI-Powered Mix & Match Magic

EverArt: AI-Powered Image Alchemy - crank out stunning visuals in seconds with mix-and-match models. Perfect for artists, ads, or just playing with pixels. No more limits, just magic." )

AI Chatbot
4.5(163 reviews)
244 saves
114 comments

Users create an average of 12 projects per month with this tool

About EverArt

What is EverArt: AI-Powered Mix & Match Magic?

EverArt is an AI-driven image generation platform integrated with Claude Desktop, enabling users to create and refine visuals through its API-powered MCP server. By leveraging advanced models like FLUX1.1, SD3.5, and Recraft series, it offers flexible creative control for diverse projects. The tool seamlessly connects with your workflow via Docker or NPX, allowing rapid prototyping and real-time browser previews.

How to Use EverArt: AI-Powered Mix & Match Magic?

1. Install Dependencies: Run npm install and set your EVERART_API_KEY.
2. Configure Deployment: Choose Docker (docker run...) or NPX (npx @modelcontextprotocol/server-everart).
3. Generate Images: Use the generate_image tool with parameters like prompt, model ID, and image count. Results open instantly in your browser.

EverArt Features

Key Features of EverArt: AI-Powered Mix & Match Magic?

  • Model Diversity: 5+ specialized models for realism, vector art, and creative enhancement.
  • Instant Feedback: Auto-browser preview with direct access to image URLs.
  • Scalable Setup: Deploy via Docker containers or lightweight NPX commands.
  • Batch Processing: Generate 1-10 images per request at 1024x1024 resolution.

Use Cases of EverArt: AI-Powered Mix & Match Magic?

Design Prototyping: Test UI concepts with Recraft-Vector for crisp logos.
E-commerce Product Renders: Create photorealistic variants using FLUX1.1-ultra.
Social Media Assets: Generate cohesive image grids with SD3.5 for campaigns.
Education & Presentations: Visualize abstract concepts through iterative model mixing.

EverArt FAQ

FAQ About EverArt: AI-Powered Mix & Match Magic?

  • Q: How many models are available?
    A: 5 core models with distinct specializations.
  • Q: What's the max image resolution?
    A: 1024x1024 pixels per output.
  • Q: Can I use custom prompts?
    A: Yes! Any text-based input drives the generation process.
  • Q: Is API access required?
    A: Yes, register at EverArt.dev to obtain your API key.

Content

EverArt MCP Server

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

Install

npm install
export EVERART_API_KEY=your_key_here

Config

Add to Claude Desktop config:

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"
      }
    }
  }
}

Tools

generate_image

Generates images with multiple model options. Opens result in browser and returns URL.

Parameters:

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

Models:

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

All images 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"
- Image URL: https://storage.googleapis.com/...

You can also click the URL above to view the image again.

Building w/ Docker

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

Related MCP Servers & Clients