blurLABSCO SUMMARY
Image work where the images stay put.
Local execution is the distinguishing constraint: detection, OCR and editing all run on your own machine, so photographs you are not allowed to upload are still workable. Asking in plain language — find the cat and crop around it — chains several tools in one go.
What it is
A local computer-vision toolkit for AI assistants, built on OpenCV. It crops, resizes and rotates, removes backgrounds, draws text and shapes, adds logos and watermarks, detects objects with pretrained models and extracts text with OCR — all on the machine it runs on.
What you get
- Crop, resize and rotate with precision, plus background removal
- Object detection with a range of pretrained models, chosen per call with a confidence threshold
- Text extracted from images by OCR
- Rectangles, circles, lines and arrows drawn onto an image (draw_rectangles, draw_circles, draw_lines, draw_arrows)
- Colour changes applied to an image (change_color)
- Text, logos and watermarks added
- Several tools chained by one request, so a single instruction can find, crop and annotate
- Everything runs locally — images are never sent to a server
Requirements
A local install of the imagesorcery-mcp package. Give it full paths to your files — the tools read and write images on the machine. MIT licensed, and it works with Claude, Cursor and Cline.
Setup effort
One command — pipx install imagesorcery-mcp
USE CASES
01
Marking up a screenshot for someone else
Rectangles and arrows point at the thing you mean, so a bug report shows the problem instead of describing where to look.
02
Highlighting a detail in a photo
Circles and colour changes call out one region, which is what turns a photo into an illustration of a specific point.
03
Centring an image on its subject
Detection locates the object you name and the crop is taken around it, so centring the subject is one request rather than a manual selection.
04
Reading text that only exists inside an image
OCR pulls the text out of a screenshot or a scan, so it can be searched, quoted or filled into a form.
05
Sorting a folder by what is in the pictures
Detection runs across a directory, so photos can be filtered by their contents — moving every picture with a pet into its own folder, for instance.
17 tools
Listed in project docs. Your client may show a different list.
change_colorconfigcropdetectdraw_arrowsdraw_circlesdraw_linesdraw_rectanglesdraw_textsfillfindget_metainfoocroverlayresizerotateBEFORE YOU INSTALL
What to know first
Tools you get
17 tools named in the project's documentation.
Requires
pipx on PATH
INSTALLATION
Connect your client
Server setup
TERMINAL
pipx install imagesorcery-mcpMCP Clients
Cline
1. Load MCP documentation if you have the tool for it. 2. Run command pipx install imagesorcery-mcp 3. Run command imagesorcery-mcp --post-install 4. Create or modify *MCP-configuration file*. 5. Add the imagesorcery-mcp server configuration to the mcpServers object
CLINE
imagesorcery-mcpAny MCP client — pipx
ANY MCP CLIENT — PIPX · JSON
{
"mcpServers": {
"imagesorcery-mcp": {
"command": "imagesorcery-mcp",
"transportType": "stdio",
"timeout": 100
}
}
}Any MCP client — venv
ANY MCP CLIENT — VENV · JSON
{
"mcpServers": {
"imagesorcery-mcp": {
"command": "<YOUR_PATH_TO_VENV>/bin/imagesorcery-mcp",
"transportType": "stdio",
"timeout": 100
}
}
}Any MCP client — Windows
ANY MCP CLIENT — WINDOWS · JSON
{
"mcpServers": {
"imagesorcery-mcp": {
"command": "imagesorcery-mcp.exe",
"transportType": "stdio",
"timeout": 100
}
}
}Any MCP client — HTTP
ANY MCP CLIENT — HTTP · JSON
{
"mcpServers": {
"imagesorcery-mcp": {
"url": "http://127.0.0.1:8000/mcp",
"transportType": "http",
"timeout": 100
}
}
}
