MeiGen-AI-Design-MCP MCP — Anwendungsfälle, Installieren & Live-Demo

Warum nutzen

Hauptfunktionen

1,500+ curated prompts with visual previews
Prompt enhancer converts rough ideas into production-grade prompts
ComfyUI workflow templates managed from the agent
Backend-agnostic: local ComfyUI, MeiGen Cloud, or OpenAI-compatible

Live-Demo

In der Praxis

meigen-ai-design.replay ▶ bereit

0/0

Installieren

Wählen Sie Ihren Client

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "meigen-ai-design": {
      "command": "npx",
      "args": [
        "-y",
        "MeiGen-AI-Design-MCP"
      ],
      "_inferred": true
    }
  }
}

Öffne Claude Desktop → Settings → Developer → Edit Config. Nach dem Speichern neu starten.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "meigen-ai-design": {
      "command": "npx",
      "args": [
        "-y",
        "MeiGen-AI-Design-MCP"
      ],
      "_inferred": true
    }
  }
}

Cursor nutzt das gleiche mcpServers-Schema wie Claude Desktop. Projektkonfiguration schlägt die globale.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "meigen-ai-design": {
      "command": "npx",
      "args": [
        "-y",
        "MeiGen-AI-Design-MCP"
      ],
      "_inferred": true
    }
  }
}

Klicken Sie auf das MCP-Servers-Symbol in der Cline-Seitenleiste, dann "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "meigen-ai-design": {
      "command": "npx",
      "args": [
        "-y",
        "MeiGen-AI-Design-MCP"
      ],
      "_inferred": true
    }
  }
}

Gleiche Struktur wie Claude Desktop. Windsurf neu starten zum Übernehmen.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "meigen-ai-design",
      "command": "npx",
      "args": [
        "-y",
        "MeiGen-AI-Design-MCP"
      ]
    }
  ]
}

Continue nutzt ein Array von Serverobjekten statt einer Map.

~/.config/zed/settings.json

{
  "context_servers": {
    "meigen-ai-design": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "MeiGen-AI-Design-MCP"
        ]
      }
    }
  }
}

In context_servers hinzufügen. Zed lädt beim Speichern neu.

claude mcp add meigen-ai-design -- npx -y MeiGen-AI-Design-MCP

Einzeiler. Prüfen mit claude mcp list. Entfernen mit claude mcp remove.

Anwendungsfälle

Praxisnahe Nutzung: MeiGen-AI-Design-MCP

Generate a batch of on-brand marketing images with MeiGen

👤 Marketers, solo founders, content creators ⏱ ~20 min intermediate

Wann einsetzen: You need 10 variations of a hero image in a consistent style for an ad test.

Voraussetzungen

A generation backend — Local ComfyUI on 127.0.0.1:8188, MeiGen Cloud token, or OpenAI-compatible image API key

Ablauf

Find a reference style

Search the MeiGen gallery for 'minimalist SaaS hero illustration'. Show me the top 5 with previews.✓ Kopiert

→ Gallery results with prompt IDs you can reuse
Enhance your specific idea in that style

Enhance this into a production prompt in the style of gallery entry #234: 'a workspace dashboard for a tax-filing tool, warm palette'.✓ Kopiert

→ Detailed prompt with style modifiers and negative prompts
Generate 10 variations

Generate 10 images from the enhanced prompt, varying the seed. Save to ./assets/hero/.✓ Kopiert

→ 10 PNGs in the folder

Ergebnis: A folder of on-brand variants ready for A/B testing.

Fallstricke

Cloud provider cost spike from large batches — Start batch at 2 to sanity-check quality, set a budget_cap via manage_preferences
Local ComfyUI out of VRAM on large batches — Reduce resolution or batch_size in the workflow template

Kombinieren mit: filesystem

Learn image prompting by iterating on the MeiGen gallery

👤 Designers new to AI image workflows ⏱ ~15 min beginner

Wann einsetzen: You want to understand why certain prompts work before writing your own.

Ablauf

Browse the gallery by theme

Show me the top 10 trending prompts in the 'product photography' theme. Include the full prompt text.✓ Kopiert

→ Full prompts with structure visible
Dissect structure

For entry #5, break down the prompt into: subject, style, lighting, camera, modifiers. What makes it work?✓ Kopiert

→ Annotated breakdown

Ergebnis: You understand the anatomy of a working prompt — reusable knowledge.

Swap ComfyUI workflows from Claude without opening the UI

👤 ComfyUI power users ⏱ ~10 min advanced

Wann einsetzen: You maintain multiple workflows (SDXL, Flux, inpaint) and want to switch based on task.

Voraussetzungen

Local ComfyUI — github.com/comfyanonymous/ComfyUI; default port 8188

Ablauf

List saved templates

Use comfyui_workflow to list my saved workflow templates.✓ Kopiert

→ Templates by name and purpose
Load and run

Load the 'flux-portrait' template, inject my prompt, run and save the output.✓ Kopiert

→ Image saved; workflow JSON cached for reuse

Ergebnis: Faster iteration without leaving the chat.

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

meigen-ai-design + filesystem

Generate and immediately organize into project folders

Generate 5 hero variants and save them under ./campaigns/{timestamp}/ with a manifest.json noting seed + prompt.✓ Kopiert

meigen-ai-design + claude-talk-to-figma

Design in Figma → refine with MeiGen → drop back into the Figma frame

Export the selected Figma frame's content brief, enhance with MeiGen, generate 3 options, import back into a new frame.✓ Kopiert

Werkzeuge

Was dieses MCP bereitstellt

Werkzeug	Eingaben	Wann aufrufen	Kosten
search_gallery	query: str, theme?: str, limit?: int	Find a starting style	0
get_inspiration	prompt_id: str	Expand a gallery hit into copyable prompt text	0
enhance_prompt	rough_idea: str, style_ref?: prompt_id	Convert a rough idea to a production prompt	0 or 1 API call
list_models		See what providers are configured	0
comfyui_workflow	action: list\|load\|run, name?, params?	Drive a local ComfyUI instance	Local compute
manage_preferences	style?, aspect?, model?, budget_cap?	Set defaults once	0
generate_image	prompt, negative?, aspect?, model?, count?	Actually produce images	Per-image, backend-dependent

Kosten & Limits

Was der Betrieb kostet

API-Kontingent: Gallery browsing: unlimited. Generation: depends on backend
Tokens pro Aufruf: Prompt ops: 500–3000. Image results: no tokens (paths only)
Kosten in €: Free for browse/enhance; generation billed by chosen backend
Tipp: Iterate the prompt at low resolution (512px), only upscale the winner

Sicherheit

Rechte, Secrets, Reichweite

Credential-Speicherung: Provider tokens in env vars (MEIGEN_TOKEN, OPENAI_API_KEY, etc.)

Datenabfluss: Gallery: meigen.ai. Generation: configured provider endpoint only

Fehlerbehebung

Häufige Fehler und Lösungen

generate_image returns 'no backend configured'

Run /meigen:setup or manually set one of: COMFYUI_URL, MEIGEN_TOKEN, OPENAI_API_KEY

Prüfen: list_models should show at least one provider

ComfyUI connection refused

Start ComfyUI (python main.py) and confirm it binds to 127.0.0.1:8188

Prüfen: curl http://127.0.0.1:8188/system_stats

Enhanced prompts are generic

Pass a style_ref from the gallery so the enhancer has an anchor

Alternativen

MeiGen-AI-Design-MCP vs. andere

Alternative	Wann stattdessen	Kompromiss
Direct ComfyUI MCP	You only want ComfyUI control, no gallery/enhancer	No curated prompts or cloud fallback
OpenAI Images API directly	You just want dall-e / gpt-image from code	No style library, no local option

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen