describe_imageLABSCO SUMMARY
The image files on your disk become things an assistant can read.
It handles the whole loop around an image — describe it, interrogate one aspect, compare it against another, read the raw file metadata — and caches what it has already looked at, so an iteration loop does not turn into an API bill.
What it is
An image analysis server built on OpenAI's vision models, running locally against files on your disk. Results are cached, so asking the same thing twice does not bill twice. It also generates and edits images from text prompts using DALL-E and GPT-Image-1.
What you get
- A full description of an image at a path, or an answer to the specific question you attach to it
- Targeted analysis of one aspect — objects, text, colours, composition or emotion — rather than a general description
- Two images compared, with the focus of the comparison set by you
- Technical metadata read off the file itself, for PNG, JPEG, GIF and WebP
- A cache you can inspect and clear, so repeated analysis is free and stale results are removable
Requirements
uv and Python; the server is launched from the repo directory. An OpenAI API key in the environment — the vision and generation calls bill to your OpenAI account. It reads images by path, so the files have to be on the machine running it.
Setup effort
Build from source — git clone https://github.com/kareemaly/ai-image-mcp
USE CASES
01
Getting the text out of a screenshot
Aim the analysis at text specifically rather than asking for a general description, so what comes back is the content and not a summary of the layout.
02
Working out what changed between two versions
Hand it both files and say what you are comparing — layout, colour, content — and read the differences instead of flipping between windows.
03
Writing alt text for a batch of images
Ask for a description with the prompt that matches your house style, and check dimensions and format in the same pass.
04
Keeping an iteration loop cheap
The cache holds what has already been analysed — check what is in it, and clear it when the file behind a path has changed.
10 tools
Listed in project docs. Your client may show a different list.
analyze_image_contentcompare_imagesget_image_metadatagenerate_imageedit_imagecreate_image_variationslist_generated_imagesget_cache_infoclear_image_cacheBEFORE YOU INSTALL
What to know first
Tools you get
10 tools named in the project's documentation.
Requires
- uv on PATH
- Python 3.13 or later
- OPENAI_API_KEY in your environment
Where it runs
Both documented clients run the server on your machine.
INSTALLATION
Connect your client
You clone this one yourself.
Server setup
TERMINAL
git clone https://github.com/kareemaly/ai-image-mcp
cd ai-image-mcp
uv add "mcp[cli]" openai pillow requestsMCP Clients
Claude Desktop, Cursor
JSON
{
"mcpServers": {
"ai-image-mcp": {
"command": "uv",
"args": [
"--directory",
"<YOUR_PATH_TO_AI_IMAGE_MCP>",
"run",
"main.py"
],
"env": {
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
}
}
}
}
