cf-image-gen MCP Server

Generate images and video from text prompts using Cloudflare Workers AI (Stable Diffusion) or Google Gemini models via Cloudflare AI Gateway.

Architecture

Text Prompt → cf-image-gen MCP Server → Cloudflare AI Gateway
                                           ├── Workers AI (Stable Diffusion XL)
                                           ├── Gemini Image Models (generateContent)
                                           └── Gemini Text Models (Interactions API)

Related MCP server: pixel-surgeon-mcp

Models

Workers AI (Direct)

Google Gemini (via AI Gateway)

Use google-ai-studio/{modelName} format.

Image Models (generateContent)

Text Models (Interactions API)

Prerequisites

• Node.js 18+

• Cloudflare account with:

  • Account ID

  • API Token (Workers AI)

  • AI Gateway ID

  • AI Gateway Auth Token (for Gemini models)

• Google AI Studio API key (for Gemini models)

Environment Variables

Usage

Via MCP Tool

{
  "prompt": "a samurai warrior standing on a mountain at sunset, pixel art style, 8-bit game aesthetic",
  "model": "google-ai-studio/gemini-3.1-flash-image"
}

Or with Stable Diffusion (default):

{
  "prompt": "a red apple on white background"
}

Example Output

Gemini 3.1 Flash Image — google-ai-studio/gemini-3.1-flash-image

Prompt: "a samurai warrior standing on a mountain at sunset, pixel art style, 8-bit game aesthetic"

How It Works

1. Workers AI path: Direct call to POST /accounts/{id}/ai/run/{model} with Cloudflare API Token

2. AI Gateway path: Routes through gateway.ai.cloudflare.com/v1/{account}/{gateway}/

   • Image-capable models → v1beta/models/{model}:generateContent with generationConfig.responseModalities: ["IMAGE"]

   • Text-only models (gemini-3-flash*) → v1beta/interactions with plain string input

Development

# Install dependencies
cd .opencode/mcp/cf-image-gen
npm install

# Run standalone (stdio)

# Configure in opencode.jsonc as MCP server

License

MIT