mahan-ym/ImageAlfred

Image Alfred

ImageAlfred is an image Model Context Protocol (MCP) tool designed to streamline image processing workflows

<a href=https://huggingface.co>

🚀 Try it in Hugging Face Space

Demo

Maintainers

Mahan-ym | Mahan Yarmohammad

Soodoo | Saaed Saadatipour

Tools

• Gradio: Serving user interface and MCP server.
• Modal.com: AI infrastructure making all the magic 🔮 possible.
• SAM: Segment Anything model by meta for image segmentation and mask generation.
• CLIPSeg: Image Segmentation using CLIP. We used it as a more precise object detection model.
• OWLv2: Zero-Shot object detection (Better performance in license plate detection and privacy preserving use-cases).
• HuggingFace: Downloading SAM and using Space for hosting.

Getting Started

Prerequisites

• Python 3.12+
• uv (a fast Python package installer and virtual environment manager)

Installation

It will create virtual environment, activate it, install dependecies and setup modal

make install

Running the App

This will deploy the Modal container and launch the Gradio interface for ImageAlfred.

make run

Try it in Claude Desktop

Make sure Node.js is installed.

• for testing from Hugging Face space (first check it's running status).

{
    "mcpServers": {
        "Image Alfred": {
            "command": "npx",
            "args": [
                "mcp-remote",
                "https://agents-mcp-hackathon-imagealfred.hf.space/gradio_api/mcp/sse",
                "--transport",
                "sse-only"
            ]
        }
    }
}

• for lacal testing

{
    "mcpServers": {
        "Local Image Alfred": {
            "command": "npx",
            "args": [
                "mcp-remote",
                "http://127.0.0.1:7860/gradio_api/mcp/sse",
                "--transport",
                "sse-only"
            ]
        }
    }
}

License

This project is licensed under the terms of the LICENSE file in this repository.