Happy slice of mcp pizzaMCP.pizza

MeiGen-AI-Design-MCP

MCP.Pizza Chef: jau123

This tool connects your AI assistant to eleven leading image and video generation models, including options associated with OpenAI, Midjourney, and Google, plus a library of more than 1,400 ready-made prompts for tasks like product photography, logos, and marketing visuals. It works inside Claude Code, Cursor, Windsurf, and Roo Code, and can also run offline through a locally installed ComfyUI setup on your own computer. You will need to enter an API key or connect a backend during a short setup step before generating your first image.

Images/Design

Use This MCP server To

Create several product photo variations at once Design a logo from a plain text description Turn a still product photo into a short video clip Generate marketing images for a new product launch Pull ready-made prompts from a library of 1,400+ options Try different AI art models without switching apps Add a model or lifestyle scene to a product shot

README

MeiGen AI Design MCP Mentioned in Awesome MCP Servers Featured in wshobson/agents

Open-source MCP server for AI image & video generation — native to every major AI coding tool
11 leading models (GPT Image 2 · Nanobanana 2 · Seedream 5.0 · Midjourney V8.1 · Flux 2 Klein · Grok Imagine · Seedance 2.0 · Happyhorse 1.0 · Veo 3.1 · Grok Video · local ComfyUI) · 1,446 curated prompts · parallel sub-agent orchestration · standalone CLI mode. Works in Claude Code, Cursor, Codex, Windsurf, Roo Code, OpenClaw, Hermes Agent, and any MCP-compatible host.

npm version npm downloads MCP Server ComfyUI Support MIT Discord

Quick Start • Demo • Features • Providers • Commands

English | 中文

What Is This?

An MCP server that turns any AI coding tool into a professional design assistant. 8 tools + a curated 1,446-prompt library let it design logos, render product shots, animate stills into video, and orchestrate parallel batch variations. Works in Claude Code, Cursor, Codex, Windsurf, Roo Code, OpenClaw, Hermes Agent, and any MCP-compatible host — with the MeiGen platform, any OpenAI-compatible API, or your local ComfyUI as the backend.

MeiGen-AI-Design-MCP FAQ

Can I use this to create product photos for my online store?
Yes — describe the product and style you want, and it generates several image options, including versions with a model or a lifestyle setting, within a couple of minutes.
Can I use this to turn a photo into a short video?
Yes — several of the supported models can animate a still image into a brief video clip, which is handy for social media posts or product showcases.
Which apps does this work with?
It works with Claude Code, Cursor, Windsurf, and Roo Code, along with any other AI assistant that supports this type of connection. A standalone command-line version is also available for anyone who wants image generation without an AI assistant at all.
Do I need an account or an API key to use it?
Yes. You will need a key from one of three sources: the MeiGen cloud service, an OpenAI-compatible provider such as OpenAI or Google, or your own locally installed ComfyUI setup. A short setup wizard walks you through entering it.
Is this hard to set up?
It is a light setup step — you run one command to add it to your AI assistant, then answer a few questions in a guided wizard to connect your chosen image service.
Can I generate several image variations at the same time?
Yes — you can ask for multiple design directions in a single request, and they are created in parallel rather than one at a time.
Do I need design experience to use this?
No. You describe what you want in plain language, and you can also draw from a built-in library of more than 1,400 ready-made prompts if you are not sure how to phrase your request.
Can I use this without an internet connection?
Yes, if you set it up with a locally installed ComfyUI backend, which runs on your own computer's graphics card instead of a cloud service.