meigen-ai-design-mcp

# MeiGen AI Design MCP > Skill by [ara.so](https://ara.so) — Design Skills collection. MeiGen AI Design MCP turns AI coding tools into professional design assistants. It provides 8 MCP tools for generating images and videos, searching 1,446 curated prompts, enhancing prompts with AI, and managing design workflows. Works with Claude Code, Cursor, Windsurf, Roo Code, OpenClaw, and any MCP-compatible host. **Backend options:** - **MeiGen Cloud** — 9 models (GPT Image 2, Nanobanana 2, Midjourney V8.1, Flux 2 Klein, Seedream 5.0, Seedance 2.0, Happyhorse 1.0, Veo 3.1) - **OpenAI-compatible API** — bring your own key and endpoint - **Local ComfyUI** — run on your own GPU, full control over workflows ## Installation ### Claude Code Plugin (Recommended) ```bash # Add marketplace and install /plugin marketplace add jau123/MeiGen-AI-Design-MCP /plugin install meigen@meigen-marketplace ``` **Restart Claude Code** after installation. Then run the setup wizard: ```bash /meigen:setup ``` ### Cursor / VS Code / Windsurf / Roo Code ```bash # One command auto-configures for your 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) ``` ### OpenClaw ```bash # Full plugin (commands + skills + MCP server) openclaw bundles install clawhub:meigen-ai-design # Or skill only npx clawhub@latest install creative-toolkit ``` ### Manual MCP Configuration Add to your MCP config file (`.mcp.json`, `claude_desktop_config.json`, etc.): ```json { "mcpServers": { "meigen": { "command": "npx", "args": ["-y", "meigen@1.3.1"], "env": { "MEIGEN_API_TOKEN": "meigen_sk_..." } } } } ``` ### CLI Mode (No MCP Host Required) ```bash # Set token once export MEIGEN_API_TOKEN=meigen_sk_... # Generate npx meigen gen --prompt "a calico cat in a sunlit kitchen" npx meigen gen -p "tech logo" -m midjourney-v8.1 -r 1:1 npx meigen gen -p "product shot" --ref ~/Desktop/bottle.jpg ``` ## Configuration ### Environment Variables ```bash # MeiGen Cloud API token (get at https://www.meigen.ai → Settings → API Keys) MEIGEN_API_TOKEN=meigen_sk_... # OpenAI-compatible API (optional) OPENAI_API_KEY=sk-... OPENAI_BASE_URL=https://api.openai.com/v1 # ComfyUI (optional) COMFYUI_URL=http://localhost:8188 # Output directories (optional) MEIGEN_OUTPUT_DIR=~/Pictures/meigen MEIGEN_VIDEO_OUTPUT_DIR=~/Movies/meigen ``` ### Project-Level Config Create `.meigen.json` in your project root: ```json { "provider": "meigen", "meigenApiToken": "${MEIGEN_API_TOKEN}", "defaultModel": "nanobanana-2", "defaultAspectRatio": "16:9", "comfyuiUrl": "http://localhost:8188", "comfyuiDefaultWorkflow": "txt2img", "openaiApiKey": "${OPENAI_API_KEY}", "openaiBaseUrl": "https://api.openai.com/v1" } ``` ## MCP Tools ### search_gallery Search 1,446 curated prompts with visual previews. Free, no API key required. ```typescript // AI agent will call this when user says: // "find inspiration for product photography" // "search for logo designs" // "show me nature landscape prompts" { "keywords": "product photography", "style": "commercial", "limit": 10 } ``` ### get_inspiration Get full prompt, all images, and metadata for a gallery entry. Free. ```typescript // After search_gallery, get full details { "id": "12345" } ``` ### enhance_prompt Transform a brief idea into a professional image prompt. Free. ```typescript // User says: "a coffee cup" // AI calls enhance_prompt to expand into: // "A ceramic coffee cup on a wooden table, warm morning light streaming through window, shallow depth of field, product photography style, commercial quality, 4K detail" { "userPrompt": "a coffee cup", "style": "commercial", "aspectRatio": "16:9" } ``` ### list_models List available models across all configured providers. Free. ```typescript // Returns models from MeiGen Cloud, OpenAI, and local ComfyUI {} // No parameters ``` ### generate_image Generate an image. Requires API key. Routes to best available provider automatically. ```typescript // Basic generation { "prompt": "a calico cat in a sunlit kitchen, photorealistic, 4K detail", "model": "nanobanana-2", "aspectRatio": "16:9" } // With reference image (local file auto-uploaded) { "prompt": "product hero shot, professional lighting", "model": "gpt-image-2", "aspectRatio": "1:1", "referenceImagePath": "/Users/you/Desktop/bottle.jpg" } // With specific provider { "prompt": "logo design, minimal, tech startup", "provider": "comfyui", "workflowName": "txt2img", "aspectRatio": "1:1" } ``` ### generate_video Generate a video via MeiGen platform. Requires API key. Saves MP4 to `~/Movies/meigen/`. ```typescript // Text-to-video { "prompt": "a cat walking through a garden, cinematic", "model": "seedance-2.0-fast", "duration": 5 } // Image-to-video (first frame) { "prompt": "camera slowly zooms in", "model": "happyhorse-1.0", "duration": 5, "firstFramePath": "/Users/you/Desktop/scene.jpg" } // Veo 3.1 (longest duration) { "prompt": "product rotation, studio lighting", "model": "veo-3.1", "duration": 10 } ``` **Video models:** - `seedance-2.0-fast` — 5s, fastest - `seedance-2.0-pro` — 5s, higher quality - `happyhorse-1.0` — 5s, cinematic - `veo-3.1` — up to 10s, best quality ### comfyui_workflow Manage ComfyUI workflow templates. Free. ```typescript // List workflows { "action": "list" } // View workflow details { "action": "view", "name": "txt2img" } // Import new workflow (from ComfyUI API format JSON) { "action": "import", "name": "my-flux-workflow", "workflow": { /* ComfyUI API format workflow */ } } // Delete workflow { "action": "delete", "name": "old-workflow" } ``` ### manage_preferences Remember user's preferred style, aspect ratio, model, and favorite prompts. Free. ```typescript // Set preferences { "action": "set", "preferences": { "defaultModel": "midjourney-v8.1", "defaultAspectRatio": "1:1", "favoriteStyle": "minimal modern", "favoritePrompts": ["tech logo", "product photography"] } } // Get preferences { "action": "get" } ``` ## Slash Commands ```bash # Quick generate — skip conversation /meigen:gen a calico cat in sunlit kitchen # Search prompts /meigen:find product photography # Browse models /meigen:models # Setup wizard /meigen:setup ``` ## CLI Usage ### Basic Generation ```bash # Simple prompt npx meigen gen --prompt "a calico cat in a sunlit kitchen" # Specific model + aspect ratio npx meigen gen -p "tech logo" -m midjourney-v8.1 -r 1:1 # With reference image npx meigen gen -p "product hero shot" --ref ~/Desktop/bottle.jpg # Specific provider npx meigen gen -p "portrait" --provider openai -m gpt-image-2 # ComfyUI workflow npx meigen gen -p "landscape" --provider comfyui --workflow flux-dev ``` ### Advanced Options ```bash # Submit only (no polling) — good for CI npx meigen gen -p "..." --no-wait # Machine-readable JSON output npx meigen gen -p "..." --json | jq -r '.imageUrls[0]' # Custom output directory MEIGEN_OUTPUT_DIR=/tmp/images npx meigen gen -p "..." # Video generation (MeiGen Cloud only) npx meigen gen -p "cat walking" --video -m seedance-2.0-fast --duration 5 # Video from first frame npx meigen gen -p "zoom in" --video --first-frame scene.jpg ``` ### All CLI Flags ``` -p, --prompt <text> Image description (required) -m, --model <name> AI model (default: nanobanana-2) -r, --aspect-ratio <ratio> Aspect ratio: 1:1, 16:9, 9:16, etc. (default: 16:9) --ref, --reference <path> Reference image (local file, auto-uploaded) --provider <name> Force provider: meigen, openai, or comfyui --workflow <name> ComfyUI workflow name (when provider=comfyui) --video Generate video instead of image --duration <seconds> Video duration: 5 or 10 (default: 5) --first-frame <path> First frame image for video (local file) --no-wait Submit only, don't poll for completion --json Machine-readable JSON output ``` ## Common Patterns ### Parallel Batch Generation When a user asks for multiple variations, MeiGen uses specialized sub-agents to generate in parallel: ```typescript // User says: "Create 4 product images for this perfume" // AI will: // 1. Call enhance_prompt 4 times to craft distinct prompts // 2. Spawn image-generator sub-agents to run generate_image in parallel // 3. Return all 4 images in ~2 minutes // No special code needed — MeiGen handles orchestration automatically ``` ### Reference Image Upload Local images are auto-compressed and uploaded: ```typescript // User drops ~/Desktop/bottle.jpg into chat and says: // "Make this look more professional" // AI calls: { "prompt": "professional product photography, studio lighting, white background", "model": "gpt-image-2", "aspectRatio": "1:1", "referenceImagePath": "/Users/you/Desktop/bottle.jpg" } // MeiGen auto-compresses to <10MB and uploads to MeiGen Cloud ``` ### ComfyUI Workflow Import ```typescript // 1. Export workflow from ComfyUI UI (Save API Format) // 2. Import to MeiGen { "action": "import", "name": "flux-dev-txt2img", "workflow": { "3": { "inputs": { "seed": 42, "steps": 20, "cfg": 7, "sampler_name": "euler", "scheduler": "normal", "denoise": 1, "model": ["4", 0], "positive": ["6", 0], "negative": ["7", 0], "latent_image": ["5", 0] }, "class_type": "KSampler" }, // ... rest of workflow } } // 3. Use in generate_image { "prompt": "a cat", "provider": "comfyui", "workflowName": "flux-dev-txt2img" } ``` ### Prompt Enhancement Pipeline ```typescript // User gives minimal prompt: "a logo" // AI automatically enhances before generating: // Step 1: enhance_prompt { "userPrompt": "a logo", "style": "minimal modern" } // Returns: "Minimal modern logo design, geometric shapes, bold typography, monochrome color palette, vector art style, professional brand identity, clean lines, scalable, white background" // Step 2: generate_image with enhanced prompt { "prompt": "Minimal modern logo design, geometric shapes...", "model": "midjourney-v8.1", "aspectRatio": "1:1" } ``` ### Multi-Model Workflow ```typescript // User: "Generate a logo with 3 different AI models" // AI calls list_models to see what's available