Read Images

🚀 MCP Image Reading Server

An MCP server for analyzing images through OpenRouter vision models. This server provides a simple interface to analyze images via various vision models (such as Claude-3.5-sonnet and Claude-3-opus), accessible through the OpenRouter API.

🚀 Quick Start

This MCP Image Reading Server allows you to analyze images using OpenRouter vision models. It offers a straightforward way to interact with powerful models through the OpenRouter API.

✨ Features

• Analyze images using multiple vision models like Claude-3.5-sonnet and Claude-3-opus.
• Provide a simple interface for image analysis via the OpenRouter API.

📦 Installation

To install the server, run the following command:

npm install @catalystneuro/mcp_read_images

📚 Documentation

Configuration

The server requires an OpenRouter API key, which you can obtain from OpenRouter.

Add the server to your MCP settings file (usually located at ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json for VSCode):

{
  "mcpServers": {
    "read_images": {
      "command": "read_images",
      "env": {
        "OPENROUTER_API_KEY": "your-api-key-here",
        "OPENROUTER_MODEL": "anthropic/claude-3.5-sonnet"  // Optional, default is claude-3.5-sonnet
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

💻 Usage Examples

Basic Usage

The server provides a single tool analyze_image for image analysis:

// Basic usage (using the default model)
use_mcp_tool({
  server_name: "read_images",
  tool_name: "analyze_image",
  arguments: {
    image_path: "/path/to/image.jpg",
    question: "What do you see in this picture?"  // Optional
  }
});

Advanced Usage

You can specify a particular model for analysis:

// Analyze using a specific model
use_mcp_tool({
  server_name: "read_images",
  tool_name: "analyze_image",
  arguments: {
    image_path: "/path/to/image.jpg",
    question: "What do you see in this picture?",
    model: "anthropic/claude-3-opus"  // Specify the model
  }
});