EverArt

AI image generation using various models

Catalog onlyCatalog onlySTDIO

Overview

EverArt is an AI image generation tool that allows users to create images using various models through an API.

To use EverArt, install the necessary dependencies, set up your API key, and configure Claude Desktop to utilize EverArt for image generation. Use the provided commands to generate images based on prompts.

Generates images using multiple AI models - Returns generated image URLs for easy access - Configurable image generation parameters (prompt, model, image count)

Creating unique art pieces based on descriptive prompts
Generating visual content for marketing and social media
Prototyping design concepts using AI-generated visuals

Tools

generate_image

image_countmodelprompt

Generate images using EverArt Models and returns a clickable link to view the generated image. The tool will return a URL that can be clicked to view the image in a browser. Available models: - 5000:FLUX1.1: Standard quality - 9000:FLUX1.1-ultra: Ultra high quality - 6000:SD3.5: Stable Diffusion 3.5 - 7000:Recraft-Real: Photorealistic style - 8000:Recraft-Vector: Vector art style The response will contain a direct link to view the generated image.

Last seen Apr 5, 2026

Add to your AI client

Use these steps to connect EverArt in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

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

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

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

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

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

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

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

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

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

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

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

FAQ

What image models does EverArt support?

EverArt supports multiple models such as FLUX1.1, SD3.5, and Recraft, offering various styles and qualities.

Can I customize the number of images generated?

Yes! You can specify the number of images you want in your requests.

Is there a limitation on the image prompt length?

The prompt can be of reasonable length, but it's best to keep it concise for optimal results.

Ai chatbot