Eternal AI MCP Server

The Eternal AI Model Context Protocol (MCP) server provides tools for image generation, image editing, and video generation.

Features

• 🎨 Image Generation: Generate images from text prompts with LoRA style support
• ✏️ Image Editing: Edit existing images by changing outfits, backgrounds, poses, and more
• 🎬 Video Generation: Animate static images into videos based on text prompts
• 💾 Auto-save: Automatically saves generated files to disk
• 📁 Local File Support: Use local image files directly with @filename.jpg syntax

Environment Variables

• ETERNAL_AI_API_KEY (required): Your API key from eternalai.org/api/keys.
• SAVE_FILE_PATH (optional): Directory or file path where generated files should be saved. If not set, files are saved to the current working directory.

Testing with MCP Inspector

npx @modelcontextprotocol/inspector -e ETERNAL_AI_API_KEY=your_api_key_here npx @eternalai-org/mcp-server@latest

Usage with MCP Clients

Add the following config to your MCP client:

{
  "mcpServers": {
    "eternal-ai": {
      "command": "npx",
      "args": ["-y", "@eternalai-org/mcp-server@latest"],
      "env": {
        "ETERNAL_AI_API_KEY": "your_api_key_here"
      }
    }
  }
}

[!NOTE] Using @eternalai-org/mcp-server@latest ensures that your MCP client will always use the latest version of the Eternal AI MCP server.

MCP Client configuration

To use the Eternal AI MCP server follow the instructions from Antigravity's docs to install a custom MCP server. Use the config provided above.

Use the Claude Code CLI to add the Eternal AI MCP server (guide):

claude mcp add eternal-ai --scope user -- npx @eternalai-org/mcp-server@latest -e ETERNAL_AI_API_KEY=your_api_key_here

Follow https://docs.cline.bot/mcp/configuring-mcp-servers and use the config provided above.

Follow the configure MCP guide using the standard config from above. You can also install the Eternal AI MCP server using the Codex CLI:

codex mcp add eternal-ai --env ETERNAL_AI_API_KEY=your_api_key_here -- npx @eternalai-org/mcp-server@latest

Start Copilot CLI:

copilot

Start the dialog to add a new MCP server by running:

/mcp add

Configure the following fields and press CTRL+S to save the configuration:

• Server name: eternal-ai
• Server Type: [1] Local
• Command: npx -y @eternalai-org/mcp-server@latest
• Environment variables: ETERNAL_AI_API_KEY=your_api_key_here

Click the button to install:

Or install manually:

Follow the MCP install guide, with the standard config from above. You can also install using the VS Code CLI:

code --add-mcp '{"name":"eternalai-org/eternal-ai","command":"npx","args":["-y","@eternalai-org/mcp-server@latest"],"env":{"ETERNAL_AI_API_KEY":"your_api_key_here"}}'

Click the button to install:

Or install manually:

Go to Cursor Settings -> MCP -> New MCP Server. Use the config provided above.

Use the Factory CLI to add the Eternal AI MCP server (guide):

droid mcp add eternal-ai "npx -y @eternalai-org/mcp-server@latest"

Install the Eternal AI MCP server using the Gemini CLI.

Project wide:

gemini mcp add eternal-ai npx @eternalai-org/mcp-server@latest

Globally:

gemini mcp add -s user eternal-ai npx @eternalai-org/mcp-server@latest

Alternatively, follow the MCP guide and use the standard config from above.

Follow the configure MCP guide using the standard config from above.

Go to Settings | Tools | AI Assistant | Model Context Protocol (MCP) -> Add. Use the config provided above.

The same way eternal-ai can be configured for JetBrains Junie in Settings | Tools | Junie | MCP Settings -> Add. Use the config provided above.

In Kiro Settings, go to Configure MCP > Open Workspace or User MCP Config > Use the configuration snippet provided above.

Or, from the IDE Activity Bar > Kiro > MCP Servers > Click Open MCP Config. Use the configuration snippet provided above.

Add the following configuration to your opencode.json file. If you don't have one, create it at ~/.config/opencode/opencode.json (guide):

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "eternal-ai": {
      "type": "local",
      "command": ["npx", "-y", "@eternalai-org/mcp-server@latest"],
      "env": {
        "ETERNAL_AI_API_KEY": "your_api_key_here"
      }
    }
  }
}

In Qoder Settings, go to MCP Server > + Add > Use the configuration snippet provided above.

Alternatively, follow the MCP guide and use the standard config from above.

Install the Eternal AI MCP server using the Qoder CLI (guide):

Project wide:

qodercli mcp add eternal-ai -- npx @eternalai-org/mcp-server@latest

Globally:

qodercli mcp add -s user eternal-ai -- npx @eternalai-org/mcp-server@latest

Click the button to install:

Available Tools

1. generate_image

Generate an image from a text prompt.

Parameters:

• prompt (string, required): Text description of the image to generate

• lora_config (object, optional): LoRA configuration for art styles. See available LoRA configurations for all options. Example:

  {
    "Art_style_Impressionist": 1,
    "psycho_art": 1,
    "FLUX-daubrez-DB4RZ": 1,
    "Flux_1_MechanicalBloom": 1,
    "RM_Artistify_v1_0M": 1
  }

  Available LoRA names:

  • Art_style_Impressionist - Impressionist art style
  • psycho_art - Anime art style with surreal elements
  • FLUX-daubrez-DB4RZ - Daubrez Painterly Style
  • Flux_1_MechanicalBloom - Surreal Anime-style Portrait
  • RM_Artistify_v1_0M - RandomMaxx Artistify

Example:

Generate an image of a sunset over mountains with impressionist style

2. edit_image

Edit an existing image based on a text prompt.

Parameters:

• prompt (string, required): Description of how to transform the image
• image (string, required): Image URL, base64 data URI, or local file path (use @filename.jpg)

Example:

Edit @photo.jpg: Change the outfit to a sporty top. Keep the same person, pose, lighting, and background.

3. generate_video

Animate an image into a video based on a text prompt.

Parameters:

• prompt (string, required): Description of the animation to create
• image (string, required): Image URL, base64 data URI, or local file path (use @filename.jpg)

Example:

Animate @photo.jpg: The person in the image is forming a heart shape with their both hands

Local File Support

You can use local image files directly by prefixing the filename with @:

• @image.jpg - Relative to current working directory
• @/path/to/image.jpg - Absolute path (remove leading / after @)
• /absolute/path/to/image.jpg - Absolute path without @

File Saving

Generated files are automatically saved to disk:

• If SAVE_FILE_PATH is set to a directory, files are saved there with auto-generated names
• If SAVE_FILE_PATH is set to a file path, files are saved to that location
• If SAVE_FILE_PATH is not set, files are saved to the current working directory

File names are automatically generated with timestamps: result-2026-01-27T08-01-23-708Z.jpg

Requirements

• Node.js 18.0.0 or higher
• Eternal AI API key from eternalai.org/api/keys

License

MIT

Support

For issues and questions, please visit the Eternal AI documentation.