MeiGen AI Design MCP
An MCP server for generating images and video from the agent: several models, a large prompt library and parallel tasks
- 1,801 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Calls external generation services with a key
- Saves generated files and can spend purchased credits
Install
- Works in
Manual install
{
"mcpServers": {
"meigen": {
"url": "https://www.meigen.ai/api/mcp",
"bearer_token_env_var": "MEIGEN_API_TOKEN"
}
}
}Remote HTTP server; the token is set in an environment variable.
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Calls external generation services with a key
- Saves generated files and can spend purchased credits
This is third-party code. Review the repository files before installing.
What it does
The server connects the agent to image and video generation and helps produce assets for ads and products. There is a remote option and a local npm server with more tools. It ships with a library of over a thousand ready prompt templates and prompt-improvement hints. Local generation supports MeiGen cloud, OpenAI-compatible APIs and a local ComfyUI. Several tasks can run in parallel, and there is a separate CLI for scripts.
Who it is for. For designers, marketers and content people who need image and video generation right from the agent.
Good fit when
- You need product images or ad creatives
- You want several variants of one scene at once
- You want to generate video from the agent
Not a fit when
- You cannot connect a paid external service with a key
- You only need to edit existing images by hand
Example request
Create four ad images of this perfume in different styles, one with a modelMCP
- Transport
- http, stdio
- Authentication
- API key
Environment variables
MEIGEN_API_TOKENrequired, secret- MeiGen API token for the generation skills
Limitations
The generation skills need a MeiGen key and purchased credits. Local general generation can run via OpenAI-compatible APIs or ComfyUI. Availability of the MeiGen cloud from Russia without VPN should be checked separately.
How to disable. Remove the meigen server from your MCP config or uninstall the plugin through your agent's tools.
FAQ
How does the remote server differ from local?
The local server has more tools and works with local files and ComfyUI, while the remote one is simpler to connect.
Do I need a key?
The generation skills need a MeiGen key and credits. Some general generation works via third-party compatible APIs.
Discussion
No questions or reviews yet.
Related
MCP serversMCP server for image generation and editing: Gemini, OpenAI and Seedream with automatic prompt enhancement
Hosted Magic Hour MCP server: the agent generates and edits video, images and audio through the service API
RunAPI MCP server: a catalog of 160 models for images, video, music and speech, pricing, task runs and balance
A set of skills for agents to generate and edit images, video and audio through the muapi.ai service and muapi-cli
Recraft's remote MCP server: an agent draws raster and vector images, edits a region, removes the background and upscales
A lightweight Python MCP server: an agent generates and iteratively refines images, audio and video in a local ComfyUI
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Authentication | Repository stars | Main difference |
|---|---|---|---|---|
| MeiGen AI Design MCP (this card) | yes | API key | 1,801 | |
| NanoBanana Trending Prompts | no | 750 | over 1,400 popular prompts for NanoBanana and GPT Image from X posts | |
| ImageSorcery MCP | no | not required | 339 | a local MCP server for editing and analyzing images |
| Comfy MCP | yes | not required | 341 | the official Comfy Org MCP server |
README in short
The README presents MeiGen as an MCP server for image and video generation, with a remote option and a local npm server. It covers setup via MCP config or an npx command, a library of over a thousand prompt templates and support for several models. Local generation can run through MeiGen cloud, OpenAI-compatible APIs or ComfyUI. There is a block for the agent to install it itself and a separate CLI.