# jau123/MeiGen-AI-Design-MCP

Supports GPT Image 2, Seedance & ComfyUI, with a 1,400+ prompt library, carefully crafted hooks and a multi-task orchestration system

Repository: https://github.com/jau123/MeiGen-AI-Design-MCP
Canonical: https://ross.abutalabs.com/products/meigen-ai-design-mcp
Homepage: https://meigen.ai
Language: TypeScript
License: MIT
License Family: permissive
Topics: ai-image-generation, claude, claude-code, comfyui, mcp, mcp-server, model-context-protocol, openclaw, prompt-engineering, seedance2
Last push: 2026-08-05T12:09:47+00:00

## Health v2 (maintenance only)
Score: 80/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 96, release rhythm 96, longevity 14
- inputs: {"age_days": 207, "days_push": 28, "days_rel": 28, "gap_med": 6, "n_releases_24m": 16}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1719, forks 224 (observed 2026-08-28T04:05:26.670260+00:00)

## What it is
An open-source MCP server that adds AI image and video generation capabilities to AI coding tools like Claude Code, Cursor, and Codex. It supports multiple backends (MeiGen cloud, OpenAI-compatible APIs, or local ComfyUI), a 1,446-prompt library, and parallel sub-agent orchestration for batch design tasks.

## Use cases
- generate logos and brand assets from an AI coding assistant
- render product shots with AI image models
- animate still images into videos
- run batch image generation variations in parallel
- use local ComfyUI for offline image generation
- enhance prompts with curated style-aware templates
- connect AI design tools to MCP-compatible hosts

## When to choose
- you want AI image/video generation integrated directly into Claude Code, Cursor, or another MCP host
- you need a large curated prompt library for design work
- you want to use your own local ComfyUI or OpenAI-compatible endpoint as a backend
- you need parallel batch generation of design variations

## When to avoid
- you need a standalone GUI image generator rather than an MCP tool
- your workflow doesn't involve AI coding tools or MCP-compatible hosts
- you only need simple one-off image generation without prompt engineering

## Facets
- artifact type: service
- maturity: active
- function: mcp, image-processing, prompt-engineering, agent-framework, cli, video-processing
- domain: artificial-intelligence, image-processing, developer-tools, web-design
- platform: cli, cross-platform
- tags: mcp-server, ai-image-generation, comfyui, claude-code, prompt-library, seedance, gpt-image, logo-design, batch-generation, video, nodejs, docker

## Member repositories
- jau123/MeiGen-AI-Design-MCP (main) score 80

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:26.670260+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:34:07.078451+00:00, confidence not recorded.
  - readme: https://github.com/jau123/MeiGen-AI-Design-MCP (fetched 2026-08-28T04:05:26.670260+00:00, sha 65ce950bf28d)
  - homepage: https://meigen.ai (fetched 2026-08-29T11:10:21.033877+00:00, sha 993c8852a606)
- Data as of 2026-08-30T08:39:29.467469+00:00.