image-mcp-server

image-mcp-server

This is an MCP server that receives image URLs and analyzes the image content using the GPT-4-turbo model.

Features

• Accepts image URLs as input and provides detailed analysis of the image content.
• Uses the GPT-4-turbo model for high-precision image recognition and description.
• Includes image URL validity check functionality.

Installation

# Clone the repository
git clone https://github.com/champierre/image-mcp-server.git
cd image-mcp-server
 
# Install dependencies
npm install
 
# Compile TypeScript
npm run build

Configuration

To use this server, you need an OpenAI API key. Set the following environment variable:

OPENAI_API_KEY=your_openai_api_key

MCP Server Configuration

To use with tools like Cline, add the following configuration to your MCP server configuration file:

For VSCode Claude Extension

Add the following to cline_mcp_settings.json:

{
  "mcpServers": {
    "image-analysis": {
      "command": "node",
      "args": ["/path/to/image-mcp-server/dist/index.js"],
      "env": {
        "OPENAI_API_KEY": "your_openai_api_key"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

For Claude Desktop App

Add the following to claude_desktop_config.json:

{
  "mcpServers": {
    "image-analysis": {
      "command": "node",
      "args": ["/path/to/image-mcp-server/dist/index.js"],
      "env": {
        "OPENAI_API_KEY": "your_openai_api_key"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

Usage

Once the MCP server is configured, the following tool becomes available:

• analyze_image: Receives an image URL and analyzes its content.

Example

Analyze image URL: https://example.com/image.jpg

Development

# Run in development mode
npm run dev

License

ISC