Official website: [imagesorcery.net](https://imagesorcery.net?utm_source=readme)
If you want an AI assistant working directly with Imagesorcery MCP, the imagesorcery mcp mcp server is the bridge. Official website: imagesorcery.net.
Official website: imagesorcery.net
Once connected, the assistant can call these 14 tools directly:
blur — Blurs specified rectangular or polygonal areas of an image using OpenCV. Can also invert the provided areas e.g. to blur backgroundchange_color — Changes the color palette of an imageconfig — View and update ImageSorcery MCP configuration settingscrop — Crops an image using OpenCV's NumPy slicing approachdetect — Detects objects in an image using models from Ultralytics. Can return segmentation masks (as PNG files) or polygonsdraw_arrows — Draws arrows on an image using OpenCVdraw_circles — Draws circles on an image using OpenCVdraw_lines — Draws lines on an image using OpenCVdraw_rectangles — Draws rectangles on an image using OpenCVdraw_texts — Draws text on an image using OpenCVfill — Fills specified rectangular, polygonal, or mask-based areas of an image with a color and opacity, or makes them transparent. Can also invert the provided areasfind — Finds objects in an image based on a text description. Can return segmentation masks (as PNG files) or polygonsget_metainfo — Gets metadata information about an image fileocr — Performs Optical Character Recognition (OCR) on an image using EasyOCRThe server is distributed via PyPI as imagesorcery-mcp, so most clients can run it without a manual build step. Add it to your MCP client's configuration and restart the client to pick it up — the copy-paste configs for Claude Desktop, Claude Code and Cursor are on this page.
Python 3.10 or higher - pipx (recommended) - for easy installation and virtual environment management - ffmpeg, libsm6, libxext6, libgl1-mesa-glx - system libraries required by OpenCV - Claude.app, Cline, or another MCP client Virtual environments (e.g. Docker) These dependencies are typically included with OpenCV installation and don't requireDeveloper-tool servers are usually the first ones people connect, because they turn "help me with this code" into an assistant that can actually read the repo and act on it. Imagesorcery MCP sits in that group, and the shape of its toolset — blur, change_color, config among others — tells you what it is really for. Worth comparing against the other developer tools servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.
| Tool | What it does |
|---|---|
| blur | Blurs specified rectangular or polygonal areas of an image using OpenCV. Can also invert the provided areas e.g. to blur background. |
| change_color | Changes the color palette of an image |
| config | View and update ImageSorcery MCP configuration settings |
| crop | Crops an image using OpenCV's NumPy slicing approach |
| detect | Detects objects in an image using models from Ultralytics. Can return segmentation masks (as PNG files) or polygons. |
| draw_arrows | Draws arrows on an image using OpenCV |
| draw_circles | Draws circles on an image using OpenCV |
| draw_lines | Draws lines on an image using OpenCV |
| draw_rectangles | Draws rectangles on an image using OpenCV |
| draw_texts | Draws text on an image using OpenCV |
| fill | Fills specified rectangular, polygonal, or mask-based areas of an image with a color and opacity, or makes them transparent. Can also invert the provided areas e.g. to remove background. |
| find | Finds objects in an image based on a text description. Can return segmentation masks (as PNG files) or polygons. |
| get_metainfo | Gets metadata information about an image file |
| ocr | Performs Optical Character Recognition (OCR) on an image using EasyOCR |
**For manual venv installation:**
```json
"mcpServers": {
"imagesorcery-mcp": {
"command": "/full/path/to/venv/bin/imagesorcery-mcp",
"transportType": "stdio",
"autoApprove": ["blur", "change_color", "config", "crop", "detect", "draw_arrows", "draw_circles", "draw_lines", "draw_rectangles", "draw_texts", "fill", "find", "get_metainfo", "ocr", "overlay", "resize", "rotate"],
"timeout": 100
}
}Configuration as documented by the project. Restart the client after saving.
Python 3.10 or higher - pipx (recommended) - for easy installation and virtual environment management - ffmpeg, libsm6, libxext6, libgl1-mesa-glx - system libraries required by OpenCV - Claude.app, Cline, or another MCP client Virtual environments (e.g. Docker) These dependencies are typically included with OpenCV installation and don't requireKill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.