meigen

MeiGen AI Design MCP

Turn Claude Code / OpenClaw into your personal design assistant rivaling Lovart
_{Local ComfyUI generation, API integration, 1,300+ pro prompt library, multi-direction parallel output}

Quick Start • Demo • Features • Providers • Commands

English | 中文

What Is This?

An open-source MCP Server (installed via plugin marketplace) that gives LLMs creative and aesthetic capabilities through 8 tools and carefully designed skills, enabling them to handle complex design tasks. It teaches LLMs how to use various image generation models effectively, delivering professional results through reference images and multi-direction parallel workflows.

• Works with local ComfyUI — no external API dependency; also easily integrates with any custom API
• Built-in 1,500+ curated prompt templates from nanobanana-trending-prompts and fine-tuned prompt engineering techniques that turn requirements into concrete image generation tasks
• Parallel batch generation and sub-agent execution to keep the main context window clean

See It in Action

▶ Watch demo on YouTube

Product Photo — 4 Directions in Parallel

"Create 4 product display images for this perfume, one of which should feature a model."

Process — AI uploads the reference image, crafts 4 distinct prompts, then generates all 4 in parallel:

Result — 4 creative directions delivered in under 2 minutes:

Generated images:

Quick Start

Claude Code Plugin (Recommended)

# Add the plugin marketplace
/plugin marketplace add jau123/MeiGen-AI-Design-MCP

# Install
/plugin install meigen@meigen-marketplace

Restart Claude Code after installation (close and reopen, or open a new terminal tab).

First-Time Setup

Free features work immediately after restart — try:

"Search for some creative inspiration"

To unlock image generation, run the setup wizard:

/meigen:setup

The wizard walks you through:

• Choose a provider — local ComfyUI, MeiGen Cloud, or OpenAI-compatible API
• Enter credentials — ComfyUI URL, API token, or key
• Done — restart Claude Code once more, then start generating

Cursor / VS Code / Windsurf / Roo Code

One command to set up MeiGen for any supported AI coding tool:

npx meigen init cursor      # Cursor
npx meigen init vscode      # VS Code / GitHub Copilot
npx meigen init windsurf    # Windsurf
npx meigen init roo         # Roo Code
npx meigen init claude      # Claude Code (project-level)

This writes the correct MCP config file with the right format and path for your tool. If a config file already exists, MeiGen is merged in without overwriting your other servers.

OpenClaw

Install from ClawHub, or use the CLI:

npx clawhub@latest install creative-toolkit

Our skills follow the Agent Skills open standard — copy them into your OpenClaw workspace and they work directly. For MCP tools, use OpenClaw's MCP adapter to connect the MeiGen server.

Other MCP-Compatible Hosts

Add to your MCP config (e.g. .mcp.json, claude_desktop_config.json):

{
  "mcpServers": {
    "meigen": {
      "command": "npx",
      "args": ["-y", "meigen@latest"],
      "env": {
        "MEIGEN_API_TOKEN": "meigen_sk_..."
      }
    }
  }
}

Free features (inspiration search, prompt enhancement, model listing) work without any API key.

Features

MCP Tools

Tool	Free	Description
search_gallery	Yes	Search 1,500+ curated trending prompts with visual previews (powered by nanobanana-trending-prompts)
get_inspiration	Yes	Get full prompt, all images, and metadata for any gallery entry
enhance_prompt	Yes	Transform a brief idea into a professional image prompt
list_models	Yes	List available models across all configured providers
upload_reference_image	Yes	Compress and upload a local image for use as a reference
comfyui_workflow	Yes	Manage ComfyUI workflow templates: list, view, import, modify, delete
manage_preferences	Yes	Remember your preferred style, aspect ratio, model, and favorite prompts
generate_image	Key	Generate an image — routes to the best available provider automatically

Slash Commands

Command	Description
/meigen:gen <prompt>	Quick generate — skip conversation, go straight to image
/meigen:find <keywords>	Search 1,300+ curated prompts for inspiration
/meigen:models	Browse and switch AI models for this session
/meigen:ref <file>	Upload a local image as reference, get a URL back
/meigen:setup	Interactive provider configuration wizard

Smart Agents

MeiGen uses specialized sub-agents for efficient parallel execution:

Agent	Purpose
image-generator	Executes generate_image in isolated context — enables true parallel generation
prompt-crafter	Writes multiple distinct prompts for batch generation (runs on Haiku for cost efficiency)
gallery-researcher	Deep gallery exploration without cluttering the main conversation (runs on Haiku)

Output Styles

Switch creative modes with /output-style:

• Creative Director — Art direction mode with visual storytelling, mood boards, and design thinking
• Minimal — Just images and file paths, no commentary. Ideal for batch workflows

Automation Hooks

• Config Check — Validates provider configuration on session start, guides setup if missing
• Auto-Open — Generated images automatically open in Preview (macOS)

Providers

MeiGen MCP supports three image generation backends. Configure one or multiple — the system auto-selects the best available.

ComfyUI — Local & Free

Run generation on your own GPU with full control over models, samplers, and workflow parameters. Import any ComfyUI API-format workflow — MeiGen auto-detects KSampler, CLIPTextEncode, EmptyLatentImage, and LoadImage nodes.

{
  "comfyuiUrl": "http://localhost:8188",
  "comfyuiDefaultWorkflow": "txt2img"
}

Perfect for Flux, SDXL, or any model you run locally. Your images never leave your machine.

MeiGen Cloud

Cloud API with multiple models: Nanobanana 2, Seedream 5.0, GPT image 1.5, and more. No GPU required.

Get your API token:

• Sign in at meigen.ai
• Click your avatar → Settings → API Keys
• Create a new key (starts with meigen_sk_)

{ "meigenApiToken": "meigen_sk_..." }

OpenAI-Compatible API

Bring your own API key for OpenAI (gpt-image-1.5), Together AI, Fireworks AI, or any compatible service.

{
  "openaiApiKey": "sk-...",
  "openaiBaseUrl": "https://api.openai.com",
  "openaiModel": "gpt-image-1.5"
}

All three providers support reference images. MeiGen and OpenAI-compatible APIs accept URLs directly; ComfyUI accepts both URLs and local file paths, injecting them into LoadImage nodes in your workflow.

Configuration

Interactive Setup (Recommended)

/meigen:setup

The wizard walks you through provider selection, API key entry, and ComfyUI workflow import. You can also paste a curl command from your API provider's docs — it auto-extracts the key, URL, and model.

Config File

Configuration is stored at ~/.config/meigen/config.json. ComfyUI workflows are stored at ~/.config/meigen/workflows/.

Environment Variables

Environment variables take priority over the config file.

Variable	Description
MEIGEN_API_TOKEN	MeiGen platform token
OPENAI_API_KEY	OpenAI / compatible API key
OPENAI_BASE_URL	API base URL (default: https://api.openai.com)
OPENAI_MODEL	Default model (default: gpt-image-1.5)
COMFYUI_URL	ComfyUI server URL (default: http://localhost:8188)

Privacy

MeiGen MCP respects your privacy. Here's what happens with your data:

• ComfyUI (local) — All processing stays on your machine. No data is sent externally.
• MeiGen Cloud — Prompts and reference images are sent to api.meigen.ai for generation. Generated images are stored temporarily on Cloudflare R2. See meigen.ai/privacy.
• OpenAI-compatible — Prompts and reference images are sent to the configured API endpoint. See your provider's privacy policy.
• Reference image upload — Images are compressed locally (max 2MB) and uploaded to Cloudflare R2 via gen.meigen.ai. Uploaded images expire automatically after 24 hours. No authentication required. ComfyUI users can skip uploading entirely by passing local file paths directly.
• Gallery search & prompt enhancement — Run locally against bundled data. No external API calls.

No telemetry, analytics, or tracking of any kind.

Custom Storage Backend

If you prefer to use your own S3/R2 bucket for reference image uploads, set the UPLOAD_GATEWAY_URL environment variable or uploadGatewayUrl in ~/.config/meigen/config.json to point to your own presign endpoint. The endpoint must implement:

POST /upload/presign
Content-Type: application/json

Request:  { "filename": "photo.jpg", "contentType": "image/jpeg", "size": 123456 }
Response: { "success": true, "presignedUrl": "https://...", "publicUrl": "https://..." }

The presignedUrl is used for a PUT upload, and publicUrl is the publicly accessible URL returned to the user.

License

MIT — free for personal and commercial use.