PromptShopMCP

English | 中文

A powerful MCP (Model Context Protocol) server that transforms images using simple text commands. Edit photos like a professional designer - just describe what you want in natural language!

Demo

Original Image

Prompt: add a coat to the dog

Prompt: Add a hat to it

Features

• Image Generation: Create images from text prompts using Google's Gemini models
• Image Modification: Transform existing images based on text instructions
• Resource Management: Track and manage generated images locally

Requirements

• Python 3.11 or higher
• Required API key:
  • Google Gemini API key Get key

Installation

1. Clone this repository:

   git https://github.com/Kira-Pgr/Image-Toolkit-MCP-Server.git
   cd Image-Toolkit-MCP-Server

2. Install UV (if not already installed):

   # On macOS and Linux.
   curl -LsSf https://astral.sh/uv/install.sh | sh
   # On Windows.
   powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
   # With pip.
   pip install uv

3. Install dependencies using UV:

   uv venv --python=python3.11
   source .venv/bin/activate #or .venv/Scripts/activate on Windows
   uv pip install -r requirements.txt

Usage

1. Claude Desktop Integration: Add the following configuration to your claude_desktop_config.json file to run the server directly from Claude Desktop:

   "PromptShopMCP": {
     "command": "uv",
     "args": [
       "--directory",
       "/project/dir/",
       "run",
       "mcp",
       "run",
       "/project/dir/server.py"
     ],
     "env": {
       "GEMINI_API_KEY": "key"
     }
   }

   Note: Replace the placeholder "key" value with your actual API key.
2. Cursor Integration:
   Linux/macOS: Modify the cursor.sh file to set your API key and project directory.

• In cursor settings, go to the "MCP" tab, click on Add new MCP server,
• Name the server whatever you want, and set the command to sh /absolute/path/to/cursor.sh.
• Wait for the server to start, and you can see the server and available tools.
• Then when you use the agent, it would automatically detect whether use the tools.

Windows: Modify the cursor.bat file to set your API key and project directory.

• In cursor settings, go to the "MCP" tab, click on Add new MCP server,
• Name the server whatever you want, and set the command to cmd /c C:\absolute\path\to\cursor.bat.
• Wait for the server to start, and you can see the server and available tools.
• Then when you use the agent, it would automatically detect whether use the tools.

Acknowledgements

• Google Gemini: For the image generation capabilities
• MCP: For the Model Context Protocol