back
loading skill details...
Generate images from text with multi-provider routing — supports GPT Image 2, Nanobanana 2, Midjourney V8.1 & Seedance 2
---
name: "AI Image & Video Generator — GPT Image 2, Seedance, ComfyUI"
description: Generate images and videos from text with multi-provider routing — supports GPT Image 2.0 (near-perfect text rendering), Nanobanana 2, Seedream 5.0, Midjourney V8.1 (unified photorealistic + anime), Flux 2 Klein (cheap drafts), Seedance 2.0 / Veo 3.1 / Grok Video / Agnes Video, and local ComfyUI workflows. Includes 1,446 curated prompts and style-aware prompt enhancement. Use when users want to create images/videos, design assets, animate photos, enhance prompts, or manage AI art workflows. NOT for: generic chat, code generation, document writing, video editing of existing footage, audio/TTS, or any task unrelated to AI image/video creation.
version: 1.0.37
homepage: https://github.com/jau123/MeiGen-AI-Design-MCP
metadata: {"clawdbot":{"emoji":"🎨","requires":{"bins":["mcporter","npx","node"]}}}
---
# Creative Toolkit
Generate professional AI images through a unified interface that routes across multiple providers. Search curated prompts, enhance ideas into production-ready descriptions, and manage local ComfyUI workflows — all from a single MCP server.
## Quick Start
Add the MCP server to your mcporter config (`~/.config/mcporter/config.json`):
```json
{
"mcpServers": {
"creative-toolkit": {
"command": "npx",
"args": ["-y", "meigen@1.4.0"]
}
}
}
```
Free tools (search, enhance, inspire) work immediately — no API key needed:
```bash
mcporter call creative-toolkit.search_gallery query="cyberpunk"
mcporter call creative-toolkit.enhance_prompt brief="a cat in space" style="realistic"
```
To unlock image generation, configure **one** of these providers:
| Provider | Config | What you need |
|----------|--------|---------------|
| **MeiGen Cloud** | `MEIGEN_API_TOKEN` | Token from [meigen.ai](https://www.meigen.ai) (avatar → Settings → API Keys) |
| **Local ComfyUI** | `comfyuiUrl` | A running ComfyUI instance — no external API needed |
| **Any OpenAI-compatible API** | `openaiApiKey` + `openaiBaseUrl` + `openaiModel` | Your own key from Together AI, Fireworks AI, etc. |
Set credentials in `~/.clawdbot/.env`, `~/.config/meigen/config.json`, or add an `"env"` block to the mcporter config above. See `references/providers.md` for details.
> **Sandboxed environments**: if the host can't write to the default `~/Pictures/meigen` save path, set the `MEIGEN_OUTPUT_DIR` env var to a writable directory (supports `~` expansion).
## Available Tools
### Free — no API key required
| Tool | What it does |
|------|-------------|
| `search_gallery` | Semantic search across 1,446 AI image prompts. Supports category filtering and curated browsing. Returns prompt text, thumbnails, and metadata. |
| `get_inspiration` | Get the full prompt and high-res images for any gallery entry. Use after `search_gallery` to get copyable prompts. |
| `enhance_prompt` | Expand a brief idea into a detailed, style-aware prompt with lighting, composition, and material directions. Supports realistic, anime, and illustration styles. |
| `list_models` | List all available models across configured providers with capabilities and supported features. |
### Requires configured provider
| Tool | What it does |
|------|-------------|
| `generate_image` | Generate an image from a text prompt. Routes to the best available provider. Supports aspect ratio, seed, and reference images. |
| `generate_video` | Generate a video via MeiGen (Seedance/Veo/Grok/Agnes; requires API key). Polls until the server reports a terminal state. |
| `check_generation` | Check a generation by ID — follow-up after interrupted polling; retry this instead of re-submitting to avoid double charges. |
| `generate_image` (with local paths) | Pass local file paths directly in `referenceImages` — images are auto-compressed locally (max 2MB, 2048px) and prepared for the selected provider. ComfyUI handles local files entirely within the local workflow. |
| `comfyui_workflow` | List, view, import, modify, and delete ComfyUI workflow templates. Adjust steps, CFG scale, sampler, and checkpoint without editing JSON. |
| `manage_preferences` | Save and load user preferences (default style, aspect ratio, style notes, favorite prompts). |
## Important Rules
### Never describe generated images
You **cannot see** generated images. After generation, only present the **exact** data from the tool response:
```
**Direction 1: Modern Minimal**
- Image URL: https://images.meigen.ai/...
- Saved to: ~/Pictures/meigen/2026-02-08_xxxx.jpg
```
Do NOT write creative commentary about what the image "looks like".
### Never specify model or provider
Do NOT pass `model` or `provider` to `generate_image` unless the user explicitly asks. The server auto-selects the best available provider and model.
### Midjourney V8.1
`model: "midjourney-v8.1"`. Unified general-purpose Midjourney model — handles photorealistic AND stylized/anime content in one model (no separate Niji model exposed). ~45s, accepts max 1 reference image, returns 4 candidate images per generation.
- Use for product photography, portraits, landscapes, cinematic shots, illustration, anime — V8.1 covers them all.
- Resolution: pass `resolution: "1K"` (default) or `"2K"` (costs more, best for posters/wallpapers).
- Advanced params (stylize/chaos/weird/raw/iw/sw/sv/quality) run with fixed server-side defaults and cannot be tuned from MCP. The only exception is `sref`, settable via `--sref <code>` at the end of the prompt (Midjourney style codes only — numeric like `3799554500` or text like `niji-cute-v1`; no URLs or local paths).
- Other Midjourney flags (`--ar`, `--chaos`, `--niji`, `--seed`, etc.) and legacy syntax (`::N` weights, `[a|b]` permutations) are silently stripped. Pass aspect ratio via the `aspectRatio` parameter, not `--ar`.
- Prompt enhancement: pass `style: 'realistic'` for general intent, `style: 'anime'` for anime/illustration intent — V8.1 follows the prompt and benefits from explicit anime trigger words for stylized output.
### Always confirm before generating multiple images
When the user wants multiple variations, present options first and ask which direction(s) to try. Include an "all of the above" option. Never auto-generate all variants without user confirmation.
---
## Workflow Modes
### Mode 1: Single Image
User wants one image. Write a prompt (or call `enhance_prompt` if the description is brief), generate, present URL + path.
### Mode 2: Prompt Enhancement + Generation
For brief ideas (under ~30 words, lacking visual details), enhance first:
```
1. enhance_prompt brief="futuristic city" style="realistic"
-> Returns detailed prompt with camera lens, lighting, atmospheric effects
2. generate_image prompt="<enhanced prompt>"
-> Omit aspectRatio to let MeiGen auto-infer (recommended). Pass an explicit
value like aspectRatio="16:9" only when the user asked for that ratio.
```
### Mode 3: Parallel Generation (2+ images)
User needs multiple variations — different directions, styles, or concepts.
1. Plan directions, present as a table
2. Ask user which direction(s) to try
3. Write distinct prompts for each — don't just tweak one word
4. Generate selected directions (max 4 parallel for API providers, 1 at a time for ComfyUI)
5. Present URLs + paths
### Mode 4: Multi-Step Creative (base + extensions)
User wants a base design plus derivatives (e.g., "design a logo and make mockups").
1. Plan 3-5 directions, ask user which to try
2. Generate selected direction(s)
3. Present results, ask user to approve or try another
4. Plan extensions using the approved Image URL as `referenceImages`
5. Generate extensions
Never jump from plan to generating everything at once.
### Mode 5: Edit/Modify Existing Image
User provides an image and asks for changes (add text, change background, etc.).
- Pass the image (URL or local path) as `referenceImages`, then generate with a **short, literal prompt** describing ONLY the edit
- The reference image carries all visual context — do NOT re-describe the original image
- Example prompt: "Add the text 'meigen.ai' at the bottom of this image"
### Mode 6: Inspiration Search
```
1. search_gallery query="dreamy portrait with soft light"
-> Finds semantically similar prompts with thumbnails
2. get_inspiration id="<entry_id>"
-> Get full prompt text — copy and modify for your own generation
```
### Mode 7: Reference Image Generation
Use an existing image to guide visual style. Pass URLs or local file paths directly to `referenceImages`.
```
generate_image prompt="coffee mug mockup with this logo" referenceImages=["~/Desktop/my-logo.png"]
-> Local files are auto-compressed (max 2MB, 2048px) and prepared for the selected provider
```
Reference image sources: gallery URLs, previous generation URLs, or local file paths. All providers accept local paths — they are automatically handled.
### Mode 8: ComfyUI Workflows
```
1. comfyui_workflow action="list" -> See saved workflows
2. comfyui_workflow action="view" name="txt2img" -> See adjustable parameters
3. comfyui_workflow action="modify" name="txt2img" modifications={"steps": 30}
4. generate_image prompt="..." workflow="txt2img" -> Generate
```
## Alternative Providers
You can use your own OpenAI-compatible API or a local ComfyUI instance instead of — or alongside — the default MeiGen provider. See `references/providers.md` for detailed configuration and provider comparison. For MeiGen model pricing, see https://www.meigen.ai/model-comparison.
## Troubleshooting
See `references/troubleshooting.md` for common issues, solutions, and security & privacy details.
don't have the plugin yet? install it then click "run inline in claude" again.