MeiGen AI Design MCP
MCP server for AI image & video generation across 9 models, with a 1,446-prompt library and parallel sub-agent orchestration.
Add to your client
Copy the config for your MCP client and paste it into its config file.
npx -y meigen@1.3.2Paste into ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"meigen-ai-design-mcp": {
"command": "npx",
"args": [
"-y",
"meigen@1.3.2"
],
"env": {
"MEIGEN_API_TOKEN": "meigen_sk_..."
}
}
}
}Step-by-step guides: Add to Claude Desktop · Add to Cursor · Add to Windsurf
Before you start
- Node.js with npx (server runs via `npx -y meigen@1.3.2`)
- An MCP-compatible host (Claude Code, Cursor, VS Code, Windsurf, Roo Code, OpenClaw, Hermes Agent, etc.) — or use the standalone CLI
- For image/video generation: a MeiGen API token (meigen_sk_...), an OpenAI-compatible API key + base URL + model, or a local ComfyUI server (free features need no key)
About MeiGen AI Design MCP
An MCP server for AI image and video generation that works across three backends (MeiGen Cloud, any OpenAI-compatible API, or local ComfyUI) and exposes 8 tools plus a 1,446-prompt curated library. It supports parallel batch generation via specialized sub-agents, reference-image workflows with automatic compression and upload, and a standalone CLI for shell/CI use. Compatible with Claude Code, Cursor, VS Code, Codex, Windsurf, Roo Code, OpenClaw, Hermes Agent, and any MCP host.
Tools & capabilities (8)
search_gallerySearch 1,446 curated trending prompts with visual previews (powered by nanobanana-trending-prompts). Free.
get_inspirationGet the full prompt, all images, and metadata for any gallery entry. Free.
enhance_promptTransform a brief idea into a professional image prompt. Free.
list_modelsList available models across all configured providers. Free.
comfyui_workflowManage ComfyUI workflow templates: list, view, import, modify, delete. Free.
manage_preferencesRemember your preferred style, aspect ratio, model, and favorite prompts. Free.
generate_imageGenerate an image — routes to the best available provider automatically. Local reference images are auto-compressed and uploaded. Requires a provider key.
generate_videoGenerate a video via the MeiGen platform — Seedance 2.0 (fast/pro), Happyhorse 1.0, or Veo 3.1. Supports text-to-video and first-frame image-to-video; local files auto-uploaded. Saves MP4 to ~/Movies/meigen/. Requires a provider key.
What this server can do
MeiGen AI Design MCP provides tools for these capabilities — tap one to see every MCP server that does the same:
When to use it
- Generate professional logos, product shots, and editorial imagery directly from an AI coding tool
- Produce multiple creative directions in parallel via sub-agents (e.g. 4 product display variations at once)
- Animate still images into video (text-to-video or first-frame image-to-video)
- Run fully local, offline image generation on your own GPU through ComfyUI
- Search a 1,446-prompt curated library for inspiration and enhance brief ideas into detailed prompts
- Drive AI image generation from shell scripts or CI pipelines via the standalone `meigen gen` CLI
Security notes
Free features (gallery search, prompt enhancement, model listing) run locally against bundled data with no external calls. Image/video generation requires a provider key (MEIGEN_API_TOKEN, OPENAI_API_KEY, or a ComfyUI URL). With MeiGen Cloud or an OpenAI-compatible endpoint, prompts and reference images are sent to that API; ComfyUI keeps all processing on your machine. Reference images are compressed locally (max 2MB) and uploaded to Cloudflare R2 via gen.meigen.ai (no auth, expire after 24h); ComfyUI users can skip upload by passing local paths. A custom S3/R2 upload backend can be configured via UPLOAD_GATEWAY_URL. The project states no telemetry, analytics, or tracking.
MeiGen AI Design MCP FAQ
Do I need an API key to use it?
No, not for everything. Free features — gallery search, prompt enhancement, model listing, ComfyUI workflow management, and preference memory — work immediately with no key. Only generate_image and generate_video require a provider key (MeiGen token, an OpenAI-compatible key, or a local ComfyUI URL).
Which backends are supported?
Three: MeiGen Cloud (9 image/video models, no GPU needed), any OpenAI-compatible API (bring your own key, base URL, and model — Together AI, Fireworks AI, DeepInfra, SiliconFlow, etc.), and local ComfyUI (offline, runs on your GPU). You can configure one or several; the server auto-selects the best available.
Which hosts and tools does it work with?
Claude Code (via plugin marketplace or .mcp.json), Cursor, VS Code / GitHub Copilot, Windsurf, Roo Code (one-command setup via `npx meigen init <tool>`), OpenClaw (ClawHub bundle), Hermes Agent, and any MCP-compatible host. It also ships a standalone CLI that needs no MCP host.
Where are generated files saved?
Images go to ~/Pictures/meigen/ (override with MEIGEN_OUTPUT_DIR) and videos to ~/Movies/meigen/ (override with MEIGEN_VIDEO_OUTPUT_DIR). On Linux, XDG_PICTURES_DIR / XDG_VIDEOS_DIR are honored when the override is unset.
Is my data kept private?
With local ComfyUI all processing stays on your machine. With MeiGen Cloud or an OpenAI-compatible endpoint, prompts and reference images are sent to that API. Reference images are compressed locally and uploaded to Cloudflare R2, expiring after 24 hours. The project states it does no telemetry, analytics, or tracking.
Alternatives to MeiGen AI Design MCP
Compare all alternatives →
Popular community server that feeds Figma layout data to coding agents via a Figma API token.
Generate beautiful, modern UI components from natural-language descriptions inside your IDE.
Give AI assistants full access to shadcn/ui v4 components, blocks, demos, and metadata across React, Svelte, Vue, and React Native.
Compare MeiGen AI Design MCP with: