Utilizes GPT-4-turbo model to analyze and provide detailed descriptions of images from URLs
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Image Analysis MCP Server analyze this image: https://example.com/photo.jpg"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
This is an MCP server that receives an image URL and analyzes the image content using the GPT-4o-mini model.
Takes an image URL as input and performs detailed analysis of the image's content
High-precision image recognition and explanation using the GPT-4o-mini model
Image URL validity check function
Related MCP server: Letz AI MCP
# リポジトリをクローン
git clone https://github.com/champierre/image-mcp-server.git
cd image-mcp-server
# 依存パッケージのインストール
npm install
# TypeScriptのコンパイル
npm run buildTo use this server, you will need an OpenAI API key, so set the following environment variables:
OPENAI_API_KEY=your_openai_api_keyTo use it with tools like Cline, add the following to your MCP server configuration file:
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": []
}
}
}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": []
}
}
}Once an MCP server is configured, the following tools are available:
analyze_image : Takes an image URL and analyzes its content
画像URLを分析してください: https://example.com/image.jpg# 開発モードで実行
npm run devISC
Receives an image URL and analyzes the image content using GPT-4o-mini
Inputs: imageUrl (required).
Loads an image from a local file path and analyzes its content using GPT-4o-mini. AI assistants need to provide a valid path for the server execution environment (e.g., Linux path if the server is running on WSL).
Inputs: imagePath (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 2 tools
The two tools are nearly identical in purpose—both analyze image content using GPT-4o-mini—differing only in input source (URL vs. local path). This creates high ambiguity, as an agent might easily misselect between them based on minor context cues, and they essentially duplicate functionality with no distinct operational domains.
Tool names follow a perfectly consistent verb_noun pattern with clear, descriptive suffixes ('analyze_image' and 'analyze_image_from_path'). Both use snake_case and maintain a uniform naming style, making them predictable and easy to interpret within the set.
With only 2 tools, the server feels under-scoped for an 'Image Analysis' domain, as it lacks basic operations like object detection, text extraction, or image comparison. The count is too low to support comprehensive analysis workflows, limiting agent capabilities to a single, narrowly defined task.
The toolset is severely incomplete for image analysis, missing essential functions such as image preprocessing, metadata extraction, or batch processing. It offers only one core action (analysis) in two input variants, leaving obvious gaps that will hinder agents from performing varied or advanced tasks in this domain.
Holiday photo MCP server: list and fetch personal holiday photos inline in Claude chat.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
AI image and video generation, talking avatars, consistent characters and photo packs from Claude.
Generate images and video from Claude with one API key.
