mcp-image
by shinpr·★ 110·Score 47
MCP server for AI image generation with automatic prompt optimization using Gemini or OpenAI models.
Overview
MCP Image Generator is a specialized MCP server that transforms simple text prompts into high-quality images through automatic prompt enhancement and optimized image generation. It supports multiple AI providers including Gemini (Nano Banana 2 & Pro) and OpenAI GPT Image, with three quality tiers for different needs. The server features built-in prompt optimization using a Subject-Context-Style framework, image editing capabilities, and character consistency across generations.
Try asking AI
After installing, here are 5 things you can ask your AI assistant:
When to choose this
Choose this server when you need AI-generated images without prompt engineering expertise, with automatic prompt enhancement and quality presets.
When NOT to choose this
Avoid this if you need maximum control over the exact prompt wording without any enhancement, or if you're looking for a wider variety of image generation models beyond Gemini and OpenAI.
Tools this server exposes
1 tool extracted from the READMEgenerate_imageGenerates high-quality images from text prompts with automatic optimization.
Comparable tools
Installation
Installation
Prerequisites
- Node.js 22 or higher
- Gemini API key (from Google AI Studio) or OpenAI API key
- MCP-compatible AI tool (Cursor, Claude Code, Codex)
Quick Start
For Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"mcp-image": {
"command": "npx",
"args": ["-y", "mcp-image"],
"env": {
"GEMINI_API_KEY": "your_gemini_api_key_here",
"IMAGE_OUTPUT_DIR": "/absolute/path/to/images"
}
}
}
}For Cursor
Add to your Cursor settings (global or project-specific):
{
"mcpServers": {
"mcp-image": {
"command": "npx",
"args": ["-y", "mcp-image"],
"env": {
"GEMINI_API_KEY": "your_gemini_api_key_here",
"IMAGE_OUTPUT_DIR": "/absolute/path/to/images"
}
}
}
}For Codex
Add to ~/.codex/config.toml:
[mcp_servers.mcp-image]
command = "npx"
args = ["-y", "mcp-image"]
[mcp_servers.mcp-image.env]
GEMINI_API_KEY = "your_gemini_api_key_here"
IMAGE_OUTPUT_DIR = "/absolute/path/to/images"FAQ
- Which AI providers are supported?
- The server supports Gemini (Nano Banana 2 & Pro) by default and OpenAI GPT Image when setting IMAGE_PROVIDER=openai.
- How do I control image quality?
- You can choose between three quality presets (fast, balanced, quality) via the IMAGE_QUALITY environment variable or by specifying it in your request to the AI assistant.
Compare mcp-image with
Last updated · Auto-generated from public README + GitHub signals.