image-mcp-server

@champierre

About image-mcp-server

No overview available yet

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "image-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli",
        "install",
        "@champierre/image-mcp-server",
        "--client",
        "claude"
      ]
    }
  }
}

Tools

No tools detected

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is image-mcp-server?

An MCP server that receives image URLs or local file paths and analyzes image content using the GPT-4o-mini model. It is designed for AI assistants that need automated image description and recognition.

How to use image-mcp-server?

Install manually by cloning the repository, running npm install and npm run build, or automatically via Smithery with npx -y @smithery/cli install @champierre/image-mcp-server --client claude. Set the OPENAI_API_KEY environment variable. Then add the server configuration (with node and the path to dist/index.js) to your MCP client settings (e.g., cline_mcp_settings.json or claude_desktop_config.json). Two tools become available: analyze_image (for URLs) and analyze_image_from_path (for local file paths).

Key features of image-mcp-server

Accepts image URLs or local file paths as input
Provides detailed image analysis using GPT-4o-mini
Checks validity of image URLs before analysis
Loads images from local files and encodes them as Base64

Use cases of image-mcp-server

An AI assistant analyzing an image from a web URL
An AI assistant describing an image stored on the local filesystem
Automating image content verification for workflows

FAQ from image-mcp-server

What tools does image-mcp-server provide?

analyze_image for analyzing images from a URL, and analyze_image_from_path for analyzing images from a local file path.

How should local file paths be specified when the server runs on WSL or Windows?

If the server runs on WSL, a Windows path (e.g., C:\...) must be converted to a WSL path (e.g., /mnt/c/...) before passing it to the tool. If the server runs on Windows, a WSL path must be converted to a UNC path (e.g., \\wsl$\Distro\...). Path conversion is the responsibility of the AI assistant.

What API key is required?

An OpenAI API key set as the environment variable OPENAI_API_KEY.

I see a TypeScript type error (TS7016) when building. Does it affect execution?

No, the JavaScript compilation succeeds and the server runs correctly. To silence the error, install @types/mime-types as a development dependency.

Where can I install image-mcp-server automatically?

Via Smithery using the command npx -y @smithery/cli install @champierre/image-mcp-server --client claude.

Frequently asked questions

What tools does image-mcp-server provide?

`analyze_image` for analyzing images from a URL, and `analyze_image_from_path` for analyzing images from a local file path.

How should local file paths be specified when the server runs on WSL or Windows?

If the server runs on WSL, a Windows path (e.g., `C:\...`) must be converted to a WSL path (e.g., `/mnt/c/...`) before passing it to the tool. If the server runs on Windows, a WSL path must be converted to a UNC path (e.g., `\\wsl$\Distro\...`). Path conversion is the responsibility of the AI assistant.

What API key is required?

An OpenAI API key set as the environment variable `OPENAI_API_KEY`.

I see a TypeScript type error (TS7016) when building. Does it affect execution?

No, the JavaScript compilation succeeds and the server runs correctly. To silence the error, install `@types/mime-types` as a development dependency.

Where can I install image-mcp-server automatically?

Via Smithery using the command `npx -y @smithery/cli install @champierre/image-mcp-server --client claude`.

Comments

Basic information

More Media & Design MCP servers

SVGator

Drive your SVGator account from any AI assistant. Prompt an animation, get an editable project back, and export it as SVG, Lottie, GIF, MP4, and more, then open it in the editor to finish by hand.

Lamina — On-brand product photos, video & try-ons

Lamina

Generate on brand product videos from Claude Code (or any assistant) in one line. Lamina turns a brief + your brand kit into finished product photos, video reels, and campaign banners - no prompt engineering; brand guard

Riddle Quiz Maker

Riddle.com

Creates and manages quizzes, polls, surveys, personality tests, forms, predictors, minigames and leaderboards on Riddle.com – with branching logic, custom design, live stats and embed code.

Constants

Constants AI

One workspace of tools for Claude and ChatGPT. Connect apps, generate video, music, and ads, and build new tools on demand. Generate and publish ad creative directly from your assistant.

Shotstack

Shotstack's official MCP server gives AI assistants direct access to the Shotstack video editing API, so you can produce video from a conversation instead of writing Edit JSON by hand. Available tools cover rendering vid