What is Image Mcp Server

image-mcp-server is an MCP server that analyzes the content of images using the GPT-4-turbo model by accepting image URLs.

Use cases

Use cases include analyzing images for content description, integrating with applications that require image understanding, and enhancing user interactions in software that utilizes visual data.

How to use

To use image-mcp-server, clone the repository, install dependencies, compile TypeScript, and set your OpenAI API key as an environment variable. Configure the server settings in your desired tool, such as VSCode or Claude Desktop App.

Key features

Key features include detailed analysis of image content from URLs, high-accuracy image recognition and description using the GPT-4-turbo model, and a validity check for image URLs.

Where to use

image-mcp-server can be used in fields such as image processing, machine learning applications, and any scenario requiring automated image content analysis.

image-mcp-server

日本語の README

An MCP server that receives image URLs or local file paths and analyzes image content using the GPT-4o-mini model.

Features

• Receives image URLs or local file paths as input and provides detailed analysis of the image content
• High-precision image recognition and description using the GPT-4o-mini model
• Image URL validity checking
• Image loading from local files and Base64 encoding

Installation

Installing via Smithery

To install Image Analysis Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @champierre/image-mcp-server --client claude

Manual Installation

# Clone the repository
git clone https://github.com/champierre/image-mcp-server.git # or your forked repository
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 settings to your MCP server configuration file:

For Cline

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"
      }
    }
  }
}

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"
      }
    }
  }
}

Usage

Once the MCP server is configured, the following tools become available:

• analyze_image: Receives an image URL and analyzes its content.
• analyze_image_from_path: Receives a local file path and analyzes its content.

Usage Examples

Analyzing from URL:

Please analyze this image URL: https://example.com/image.jpg

Analyzing from local file path:

Please analyze this image: /path/to/your/image.jpg

Note: Specifying Local File Paths

When using the analyze_image_from_path tool, the AI assistant (client) must specify a valid file path in the environment where this server is running.

• If the server is running on WSL:
  • If the AI assistant has a Windows path (e.g., C:\...), it needs to convert it to a WSL path (e.g., /mnt/c/...) before passing it to the tool.
  • If the AI assistant has a WSL path, it can pass it as is.
• If the server is running on Windows:
  • If the AI assistant has a WSL path (e.g., /home/user/...), it needs to convert it to a UNC path (e.g., \\wsl$\Distro\...) before passing it to the tool.
  • If the AI assistant has a Windows path, it can pass it as is.

Path conversion is the responsibility of the AI assistant (or its execution environment). The server will try to interpret the received path as is.

Note: Type Errors During Build

When running npm run build, you may see an error (TS7016) about missing TypeScript type definitions for the mime-types module.

src/index.ts:16:23 - error TS7016: Could not find a declaration file for module 'mime-types'. ...

This is a type checking error, and since the JavaScript compilation itself succeeds, it does not affect the server’s execution. If you want to resolve this error, install the type definition file as a development dependency.

npm install --save-dev @types/mime-types
# or
yarn add --dev @types/mime-types

Development

# Run in development mode
npm run dev

License

MIT