PromptShop

PromptShopMCP is an MCP server that translates natural language image editing requests into actions on your images. It leverages Gemini-based image generation and modification, background removal, image hosting, and resource tracking, all driven by simple text prompts you provide. This makes professional-level image tweaks accessible without manual tool orchestration.

How to use

Use an MCP client to connect to PromptShopMCP and issue text-based image commands. You can generate new images from prompts, modify existing images, remove backgrounds, and share results with hosted links. The server exposes tools that take natural language descriptions and return updated images, making photo editing fast and intuitive.

Practical usage patterns you can try after you have the server running:

• Generate an image from a prompt like “a sunny landscape with mountains and a lake.”
• Modify an existing image with a prompt such as “add a coat to the dog.”
• Remove the background of a photo and replace it with a clean blank or new background.
• Host a generated image so you can share a link with others.

How to install

Prerequisites you need before installation:

• Python 3.11 or higher
• Access keys for Gemini, remove.bg, and FreeImage.host
• A network path to clone or download the server code (see below for the exact commands)

Step 1: Install the MCP server code
```sh
git https://github.com/Kira-Pgr/Image-Toolkit-MCP-Server.git
cd Image-Toolkit-MCP-Server

Step 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

Step 3: Set up a Python virtual environment and install dependencies

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

Configuration and running the MCP server

Configure the MCP server to run via your client. The following example runs the server through UV and points to your server script, with the required API keys set in the environment:

{
  "type": "stdio",
  "name": "promptshop",
  "command": "uv",
  "args": [
    "--directory",
    "/project/dir/",
    "run",
    "mcp",
    "run",
    "/project/dir/server.py"
  ],
  "env": [
    {"name": "GEMINI_API_KEY", "value": "key"},
    {"name": "FREEIMAGE_API_KEY", "value": "key"},
    {"name": "REMOVEBG_API_KEY", "value": "key"}
  ]
}

Additional notes on key integrations

The MCP server relies on several external services. You will need API keys for Gemini image generation, background removal, and image hosting. Keep these credentials secure and do not expose them in public configurations.

Security and reliability

• Store API keys in secure environment variables and avoid committing them to version control.
• Run the MCP server behind authentication where possible, and monitor usage to prevent abuse.
• Regularly update dependencies to keep the server secure and compatible with Gemini, remove.bg, and hosting services.

Troubleshooting

• If the server fails to start, verify Python 3.11+ is active in the environment and that all API keys are set.
• Check that the UV runtime can access the server script path you provide in the configuration.
• Confirm network access to Gemini, remove.bg, and FreeImage.host endpoints from your host machine.

Notes

Keep your environment variables organized and documented for your team. When testing prompts, start with simple requests and gradually introduce more complex edits to verify each service integration behaves as expected.

Available tools

image_generation

Create new images from natural language prompts using Gemini models.

image_modification

Modify existing images based on text instructions such as adding objects or changing styles.

background_removal

Remove backgrounds from images using the remove.bg service.

image_hosting

Host generated images on FreeImage.host and provide shareable links.

resource_management

Track and manage generated and uploaded images for organization and reuse.