🪄 ImageSorcery MCP

ComputerVision-based 🪄 sorcery of image recognition and editing tools for AI assistants

❌ Without ImageSorcery MCP

AI assistants are limited when working with images:

• ❌ Can't modify or analyze images directly
• ❌ No ability to crop, resize, or process images
• ❌ Some LLMs can't detect objects or extract text from images
• ❌ Limited to verbal descriptions with no visual manipulation

✅ With ImageSorcery MCP

🪄 ImageSorcery empowers AI assistants with powerful image processing capabilities:

• ✅ Crop, resize, and rotate images with precision
• ✅ Draw text and shapes on images
• ✅ Detect objects using state-of-the-art models
• ✅ Extract text from images with OCR
• ✅ Get detailed image metadata
• ✅ Use a wide range of pre-trained models for object detection, OCR, and more

Just ask your AI to help with image tasks:

"copy photos with pets from frolder photos to folder pets"

"Find a cat at the photo.jpg and crop the image in a half in height and width to make the cat be centerized" 😉 Hint: Use full path to your files".

"Numerate form fields on this form.jpg with foduucom/web-form-ui-field-detection model and fill the form.md with a list of described fields" 😉 Hint: Specify the model and the confidence".

😉 Hint: Add "use imagesorcery" to make sure it will uses propper tool".

Your tool will combine multiple tools listed below to achieve your goal.

🛠️ Available Tools

😉 Hint: detailed information and usage instructions for each tool can be found in the tool's /src/imagesorcery_mcp/tools/README.md.

🚀 Getting Started

Requirements

• Python 3.10 or higher
• Claude.app, Cline, or another MCP client

Installation

For Cline just copy-paste LLM-INSTALL.md

1.  Load MCP documentation if you have the tool for it. It will give you path to *MCP-configuration file* and other needed instructions.
2.  Run command `python -m venv imagesorcery-mcp`
3.  Run command `source imagesorcery-mcp/bin/activate`
    For windows bash run command `source imagesorcery-mcp/Scripts/activate`
    For windows cmd run command `imagesorcery-mcp\Scripts\activate`
4.  Run command `pip install imagesorcery-mcp`
5.  Run command `imagesorcery-mcp --post-install`
6.  Create or modify *MCP-configuration file*.
7.  Add the `imagesorcery-mcp` server configuration to the `mcpServers` object in the *MCP-configuration file*
    `"imagesorcery-mcp": {"command": "/full/path/to/venv/bin/imagesorcery-mcp","timeout": 100}`
8.  Get available models using `get_models` tool from `imagesorcery-mcp`
9.  Attempt completion, indicating that the installation and configuration are complete.

1. Create and activate a virtual environment (Strongly Recommended): For reliable installation of all components, especially the clip package (installed via the post-install script), it is strongly recommended to use Python's built-in venv module instead of uv venv.

   python -m venv imagesorcery-mcp
   source imagesorcery-mcp/bin/activate  # For Linux/macOS
   # source imagesorcery-mcp\Scripts\activate    # For Windows

2. Install the package into the activated virtual environment: You can use pip or uv pip.

   pip install imagesorcery-mcp
   # OR, if you prefer using uv for installation into the venv:
   # uv pip install imagesorcery-mcp

3. Run the post-installation script: This step is crucial. It downloads the required models and attempts to install the clip Python package from GitHub into the active virtual environment.

   imagesorcery-mcp --post-install

What does the post-installation script do? The imagesorcery-mcp --post-install script performs the following actions:

• Creates a models directory (usually within the site-packages directory of your virtual environment, or a user-specific location if installed globally) to store pre-trained models.
• Generates an initial models/model_descriptions.json file there.
• Downloads default YOLO models (yoloe-11l-seg-pf.pt, yoloe-11s-seg-pf.pt, yoloe-11l-seg.pt, yoloe-11s-seg.pt) required by the detect tool into this models directory.
• Attempts to install the clip Python package from Ultralytics' GitHub repository directly into the active Python environment. This is required for text prompt functionality in the find tool.
• Downloads the CLIP model file required by the find tool into the models directory.

You can run this process anytime to restore the default models and attempt clip installation.

Important Notes for uv users (uv venv and uvx)

• Using uv venv to create virtual environments: Based on testing, virtual environments created with uv venv may not include pip in a way that allows the imagesorcery-mcp --post-install script to automatically install the clip package from GitHub (it might result in a "No module named pip" error during the clip installation step). If you choose to use uv venv:

  1. Create and activate your uv venv.
  2. Install imagesorcery-mcp: uv pip install imagesorcery-mcp.
  3. Manually install the clip package into your active uv venv:

     uv pip install git+https://github.com/ultralytics/CLIP.git

  4. Run imagesorcery-mcp --post-install. This will download models but may fail to install the clip Python package. For a smoother automated clip installation via the post-install script, using python -m venv (as described in step 1 above) is the recommended method for creating the virtual environment.

• Using uvx imagesorcery-mcp --post-install: Running the post-installation script directly with uvx (e.g., uvx imagesorcery-mcp --post-install) will likely fail to install the clip Python package. This is because the temporary environment created by uvx typically does not have pip available in a way the script can use. Models will be downloaded, but the clip package won't be installed by this command. If you intend to use uvx to run the main imagesorcery-mcp server and require clip functionality, you'll need to ensure the clip package is installed in an accessible Python environment that uvx can find, or consider installing imagesorcery-mcp into a persistent environment created with python -m venv.

⚙️ Configuration MCP client

Add to your MCP client these settings. If imagesorcery-mcp is in your system's PATH after installation, you can use imagesorcery-mcp directly as the command. Otherwise, you'll need to provide the full path to the executable.

"mcpServers": {
    "imagesorcery-mcp": {
      "command": "imagesorcery-mcp", // Or /full/path/to/venv/bin/imagesorcery-mcp if installed in a venv
      "transportType": "stdio",
      "autoApprove": ["detect", "crop", "get_models", "draw_texts", "get_metainfo", "rotate", "resize", "classify", "draw_rectangles", "find", "ocr"],
      "timeout": 100
    }
}

If you're using the server in HTTP mode, configure your client to connect to the HTTP endpoint:

"mcpServers": {
    "imagesorcery-mcp": {
      "url": "http://127.0.0.1:8000/mcp", // Use your custom host, port, and path if specified
      "transportType": "http",
      "autoApprove": ["detect", "crop", "get_models", "draw_texts", "get_metainfo", "rotate", "resize", "classify", "draw_rectangles", "find", "ocr"],
      "timeout": 100
    }
}

For Windows

"mcpServers": {
    "imagesorcery-mcp": {
      "command": "imagesorcery-mcp.exe", // Or C:\\full\\path\\to\\venv\\Scripts\\imagesorcery-mcp.exe if installed in a venv
      "transportType": "stdio",
      "autoApprove": ["detect", "crop", "get_models", "draw_texts", "get_metainfo", "rotate", "resize", "classify", "draw_rectangles", "find", "ocr"],
      "timeout": 100
    }
}

📦 Additional Models

Some tools require specific models to be available in the models directory:

# Download models for the detect tool
download-yolo-models --ultralytics yoloe-11l-seg
download-yolo-models --huggingface ultralytics/yolov8:yolov8m.pt

About Model Descriptions

When downloading models, the script automatically updates the models/model_descriptions.json file:

• For Ultralytics models: Descriptions are predefined in src/imagesorcery_mcp/scripts/create_model_descriptions.py and include detailed information about each model's purpose, size, and characteristics.

• For Hugging Face models: Descriptions are automatically extracted from the model card on Hugging Face Hub. The script attempts to use the model name from the model index or the first line of the description.

After downloading models, it's recommended to check the descriptions in models/model_descriptions.json and adjust them if needed to provide more accurate or detailed information about the models' capabilities and use cases.

Running the Server

ImageSorcery MCP server can be run in different modes:

• STDIO - default
• Streamable HTTP - for web-based deployments
• Server-Sent Events (SSE) - for web-based deployments that rely on SSE

About different modes:

1. STDIO Mode (Default) - This is the standard mode for local MCP clients:

   imagesorcery-mcp

2. Streamable HTTP Mode - For web-based deployments:

   imagesorcery-mcp --transport=streamable-http

   With custom host, port, and path:

   imagesorcery-mcp --transport=streamable-http --host=0.0.0.0 --port=4200 --path=/custom-path

Available transport options:

• --transport: Choose between "stdio" (default), "streamable-http", or "sse"
• --host: Specify host for HTTP-based transports (default: 127.0.0.1)
• --port: Specify port for HTTP-based transports (default: 8000)
• --path: Specify endpoint path for HTTP-based transports (default: /mcp)

🤝 Contributing

Whether you're a 👤 human or an 🤖 AI agent, we welcome your contributions to this project!

Directory Structure

This repository is organized as follows:

.
├── .gitignore                 # Specifies intentionally untracked files that Git should ignore.
├── pyproject.toml             # Configuration file for Python projects, including build system, dependencies, and tool settings.
├── pytest.ini                 # Configuration file for the pytest testing framework.
├── README.md                  # The main documentation file for the project.
├── setup.sh                   # A shell script for quick setup (legacy, for reference or local use).
├── models/                    # This directory stores pre-trained models used by tools like `detect` and `find`. It is typically ignored by Git due to the large file sizes.
│   ├── model_descriptions.json  # Contains descriptions of the available models.
│   ├── settings.json            # Contains settings related to model management and training runs.
│   └── *.pt                     # Pre-trained model.
├── src/                       # Contains the source code for the 🪄 ImageSorcery MCP server.
│   └── imagesorcery_mcp/       # The main package directory for the server.
│       ├── __init__.py          # Makes `imagesorcery_mcp` a Python package.
│       ├── __main__.py          # Entry point for running the package as a script.
│       ├── logging_config.py    # Configures the logging for the server.
│       ├── server.py            # The main server file, responsible for initializing FastMCP and registering tools.
│       ├── logs/                # Directory for storing server logs.
│       ├── scripts/             # Contains utility scripts for model management.
│       │   ├── README.md        # Documentation for the scripts.
│       │   ├── __init__.py      # Makes `scripts` a Python package.
│       │   ├── create_model_descriptions.py # Script to generate model descriptions.
│       │   ├── download_clip.py # Script to download CLIP models.
│       │   ├── post_install.py  # Script to run post-installation tasks.
│       │   └── download_models.py # Script to download other models (e.g., YOLO).
│       └── tools/               # Contains the implementation of individual MCP tools.
│           ├── README.md        # Documentation for the tools.
│           ├── __init__.py      # Import the central logger
│           └── *.py           # Implements the tool.
└── tests/                     # Contains test files for the project.
    ├── test_server.py         # Tests for the main server functionality.
    ├── data/                  # Contains test data, likely image files used in tests.
    └── tools/                 # Contains tests for individual tools.

Development Setup

1. Clone the repository:

git clone https://github.com/sunriseapps/imagesorcery-mcp.git # Or your fork
cd imagesorcery-mcp

2. (Recommended) Create and activate a virtual environment:

python -m venv venv
source venv/bin/activate # For Linux/macOS
# venv\Scripts\activate    # For Windows

3. Install the package in editable mode along with development dependencies:

pip install -e ".[dev]"

This will install imagesorcery-mcp and all dependencies from [project.dependencies] and [project.optional-dependencies].dev (including build and twine).

Rules

These rules apply to all contributors: humans and AI.

0. Read all the README.md files in the project. Understand the project structure and purpose. Understand the guidelines for contributing. Think through how it's relate to you task, and how to make changes accordingly.

1. Read pyproject.toml. Make attention to sections: [tool.ruff], [tool.ruff.lint], [project.optional-dependencies] and [project]dependencies. Strictly follow code style defined in pyproject.toml. Stick to the stack defined in pyproject.toml dependencies and do not add any new dependencies without a good reason.

2. Write your code in new and existing files. If new dependencies needed, update pyproject.toml and install them via pip install -e . or pip install -e ".[dev]". Do not install them diirectly via pip install. Check out exixisting source codes for examples (e.g. src/imagesorcery_mcp/server.py, src/imagesorcery_mcp/tools/crop.py). Stick to the code style, naming conventions, input and outpput data formats, codeode structure, arcchitecture, etc. of the existing code.

3. Update related README.md files with your changes. Stick to the format and structure of the existing README.md files.

4. Write tests for your code. Check out existing tests for examples (e.g. tests/test_server.py, tests/tools/test_crop.py). Stick to the code style, naming conventions, input and outpput data formats, codeode structure, arcchitecture, etc. of the existing tests.

5. Run tests and linter to ensure everything works:

pytest
ruff check .

In case of fails - fix the code and tests. It is strictly required to have all new code to comply with the linter rules and pass all tests.

Coding hints

• Use type hints where appropriate
• Use pydantic for data validation and serialization

📝 Questions?

If you have any questions, issues, or suggestions regarding this project, feel free to reach out to:

• Project Author: titulus via LinkedIn
• Sunrise Apps CEO: Vlad Karm via LinkedIn

You can also open an issue in the repository for bug reports or feature requests.

📜 License

This project is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License.

Shared threads will appear here, showcasing real-world applications and insights from the community. Check back soon for updates!