Skip to content
OpenMicroDrama

jau123 /MeiGen-AI-Design-MCP

Lets your AI coding assistant make images and videos over MCP
Model toolingMITEnglish README
Open on GitHubSave

About MeiGen-AI-Design-MCP

MeiGen lets Claude Code, Cursor, Codex and other AI assistants make images and videos without leaving the chat. The 1,446-prompt library, gallery search, and images through your own API key or local ComfyUI are free. MeiGen Cloud images, all video, and the five guided Skills cost purchased MeiGen credits. Those Skills are shop tools, like background removal, posters and upscaling.

Best for: Creators who run Claude Code or Cursor and want to make frames and clips from the chat.

What it does

  • 1,446 curated prompts to search, bundled offline in the npm version
  • Remote server with 14 tools, or a local npm server with 17
  • Makes first frames, then feeds them to generate_video as the start frame
  • Image models include GPT Image 2, Nanobanana 2, Seedream 5.0 and Midjourney V8.1
  • Video through Seedance 2.0, Veo 3.1, Grok Video and Agnes Video
  • Standalone meigen gen command for scripts, no MCP host needed

Quickstart

Rewritten from the README. Check the repo for the latest steps.

  1. 1
    Claude Code, remote (recommended): the command below then claude mcp login meigen
    claude mcp add --transport http meigen https://www.meigen.ai/api/mcp
  2. 2
    Codex: the command below then codex mcp login meigen
    codex mcp add meigen --url https://www.meigen.ai/api/mcp
  3. 3
    Cursor, VS Code, Windsurf or Roo Code (local, Node.js 22+ recommended): the command below (swap in vscode, windsurf or roo)
    npx -y meigen@2.0.2 init cursor
  4. 4
    For paid generation, create a key at meigen.ai/profile/api-keys and set MEIGEN_API_TOKEN. For free local images, set COMFYUI_URL (ComfyUI) or OPENAI_API_KEY, OPENAI_BASE_URL and OPENAI_MODEL (your own API) instead.
  5. 5
    Test it by asking "List the available Skills and their current prices". This spends no credits.

Models and languages

Models it works with

  • GPT Image 2
  • Nanobanana 2
  • Seedream 5.0
  • Midjourney V8.1
  • Flux 2 Klein
  • Grok Imagine
  • Seedance 2.0
  • Veo 3.1
  • Grok Video
  • Agnes Video

Interface and docs

  • English
  • Chinese

Alternatives

Other model tooling projects people compare with MeiGen-AI-Design-MCP.

MiniMax-AI

MiniMax-MCP

Plugs MiniMax speech, voice cloning, image and video tools into your MCP client

Model tooling
  • MiniMax-Hailuo-02
1.6k GitHub stars1 month agoMIT

higgsfield-ai

cli

40+ Higgsfield image, video, 3D and audio models from your terminal

Model tooling
  • Nano Banana Pro
  • Nano Banana 2 Lite
  • Gemini Omni Flash
  • +7
629 GitHub stars+8/30d14 days agoMIT

MiniMax-AI

cli

MiniMax images, video, speech and text from your terminal

Model tooling
  • MiniMax H3
  • Hailuo-2.3
  • MiniMax-M3
  • +1
2.2k GitHub stars+1/30d3 days agoNo license

deepbeepmeep

Wan2GP

Desktop app that runs open video, image and audio models on your own PC

Model tooling
  • Wan 2.1/2.2
  • MiniMax H3
  • LTX-2/2.3/2.5
  • +7
9.8k GitHub stars+79/30dyesterdayCustom license

Featured on OpenMicroDrama

Do you maintain MeiGen-AI-Design-MCP? Add this badge to your README so English speakers can find our write-up.

Featured on OpenMicroDrama
markdown
[![Featured on OpenMicroDrama](https://openmicrodrama.com/badges/featured.svg)](https://openmicrodrama.com/projects/jau123-meigen-ai-design-mcp)

The badge links to this page. Want your description changed? Email support@openmicrodrama.com.

Reviewed Oct 3, 2026. The MCP server code is MIT, but MeiGen Cloud is a paid service: API calls use purchased credits only, not the website's daily free credits. We write these descriptions ourselves. The repo's own docs are the final word.