MCP Image Generator

Provides AI-powered image generation and editing via Gemini 3 Pro Image, with prompt enhancement and high‑resolution outputs.

typescript

25

GitHub Stars

typescript

Language

4 months ago

First Indexed

3 weeks ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "shinpr-mcp-image": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-image"
      ],
      "env": {
        "GEMINI_API_KEY": "YOUR_API_KEY",
        "IMAGE_OUTPUT_DIR": "/absolute/path/to/images",
        "SKIP_PROMPT_ENHANCEMENT": "true"
      }
    }
  }
}

You can generate and edit images with an MCP server that leverages Gemini 3 Pro Image for high‑quality visuals. It also intelligently enhances prompts, supports multiple output sizes and aspect ratios, and saves results as accessible image files for easy use in your workflows.

How to use

You connect to the MCP Image Generator from compatible MCP clients such as Codex, Cursor, or Claude Code. After setting up your environment and API key, you can ask your AI to generate new images from text prompts, edit existing images with natural language instructions, and control outputs by size and aspect ratio. The server handles two stages automatically: prompt enhancement to enrich details and the actual image generation.

How to install

# Prerequisites
node -v    # should be 20 or higher

# Obtain your Gemini API key and keep it secure
# Create a project-level MCP configuration for your client (examples shown below)

Codex setup

[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"

Cursor setup

{
  "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"
      }
    }
  }
}

Claude Code setup

cd /path/to/your/project
claude mcp add mcp-image --env GEMINI_API_KEY=your-api-key --env IMAGE_OUTPUT_DIR=/absolute/path/to/images -- npx -y mcp-image

Or add globally for all projects:

claude mcp add mcp-image --scope user --env GEMINI_API_KEY=your-api-key --env IMAGE_OUTPUT_DIR=/absolute/path/to/images -- npx -y mcp-image

Optional: Skip Prompt Enhancement

If you want full control over prompts, you can disable automatic prompt enhancement. Set SKIP_PROMPT_ENHANCEMENT to true in your client configuration.

[mcp_servers.mcp-image.env]
GEMINI_API_KEY = "your_gemini_api_key_here"
SKIP_PROMPT_ENHANCEMENT = "true"
IMAGE_OUTPUT_DIR = "/absolute/path/to/images"

Available tools

generate_image

Single tool that handles all image operations. It first optimizes prompts using Gemini 2.0 Flash, then generates or edits images with Gemini 3 Pro Image. Supports optional parameters for aspect ratio, size, blending, character consistency, world knowledge, and output file naming.