MeiGen AI Design MCP is an MCP server that lets AI coding tools generate images and videos through cloud models, OpenAI-compatible APIs, or local ComfyUI, an interface for running image-generation workflows. It is for creating designs such as logos, product images, animations, and batches of visual variations from coding-agent environments. Its catalogue entries provide skills, commands, agents, a plugin, and a hook for using the server's design workflow.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/jau123/MeiGen-AI-Design-MCPWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/jau123/meigen-ai-design-mcp/setup)<a href="https://agentmods.dev/commands/jau123/meigen-ai-design-mcp/setup"><img src="https://agentmods.dev/badge/commands/jau123/meigen-ai-design-mcp/setup/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/jau123/meigen-ai-design-mcp/setup"><img src="https://agentmods.dev/badge/commands/jau123/meigen-ai-design-mcp/setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00043 | $0.00838 |
| Opus 5.5 | $0.00017 | $0.00335 |
| Sonnet 5.5 | $0.00009 | $0.00168 |
| Haiku 4.5 | $0.00004 | $0.00084 |
Grade A, and why
setup scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 16d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Guide one decision at a time. Never ask the user to paste a token, API key, authenticated curl command, or credential-bearing config into chat. Never read or print existing credential files, parse secrets from user messa How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MeiGen Setup
Guide one decision at a time. Never ask the user to paste a token, API key, authenticated curl command, or credential-bearing config into chat. Never read or print existing credential files, parse secrets from user messages, or echo key prefixes. The user enters secrets through their host's private connection settings, a private editor, or their own terminal outside this conversation.
Choose the connection
The self-hosted Claude marketplace plugin already bundles one local MCP server. Do not add a duplicate server. Other marketplace copies may package different components; inspect their own manifest before prescribing setup. /meigen:setup is a Claude command, not a command for other MCP hosts.
Public tools such as search_gallery, enhance_prompt, get_inspiration, list_models, and list_skills work without a key. Five dedicated workflows—Remove Background, Product Detail Images, Marketing Poster, AI Backgrounds, and Upscale—always require MeiGen and purchased credits. OpenAI-compatible providers support ordinary generate_image; they do not substitute for these five workflows or MeiGen video generation.
For a new MeiGen request, use OAuth account setup below. Preserve an explicitly selected existing BYOK provider for ordinary image generation. If a provider is already configured and working, avoid reconfiguration.
MeiGen account sign-in
For new users, add https://www.meigen.ai/api/mcp as a remote Streamable HTTP MCP server, choose Connect / Authenticate, and complete the host's OAuth sign-in and consent flow. Remove a fixed Authorization header when switching to OAuth. The bundled local stdio server has no OAuth login or private favorites, boards or history tools; replace/disable that connection through host settings when switching rather than adding a duplicate. If this host cannot authenticate, use a compatible host or the official ChatGPT plugin. Do not direct new users to create API keys.
Existing legacy configuration only
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 16d ago Changed · -7 lines · -5 tokens per session scan B → A c8bf689b821e
- 1mo ago Changed · -317 lines · -12 tokens per session scan D → B a1010a4c974c
- 1mo ago First seen · 363 lines · 60 tokens per session scan D 230f367549f9
setup is a command published in the GitHub repository jau123/MeiGen-AI-Design-MCP (1,789 stars, last pushed 3d ago), licensed MIT. It adds 43 tokens to every session and 838 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
onplana-connect
Sign in to the Onplana MCP server, then verify it works.
briefing
Briefing of what's new in your FeedNest feeds, grouped by topic.
whats-new
What the other people's assistants wrote to your coves.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.