Maker AI MCP

io.github.rocnubie由 GitHub 帳號 rocnubie 發布v0.1.0更新於 Oct 24, 2026

Create product photos, product videos, and UGC-style ads for Shopify, Amazon, TikTok, and

已驗證STDIO僅桌面商業與電商媒體與設計

概覽

AI 產生的概覽

向 MCP 用戶端提供 Maker AI 的唯讀參考內容:影片模式、定價、常見問題與官方連結。

可以做什麼
這個伺服器把 Maker AI 的官方知識以 MCP 工具與資源的形式提供出來。工具包括 list_video_modes、get_pricing 和 get_official_links,都回傳文字或 markdown。資源涵蓋影片生成模式、定價、簡短常見問題與官方連結,另有兩個提示詞可協助概述產品,或依創作意圖挑選影片模式。它是唯讀的,本身不會生成圖片或影片。
適用情境
當助理需要關於 Maker AI 影片生成模式、定價入口或官方連結的準確、最新資訊時使用,例如比較電商內容工具或撰寫需求簡報時。若只想生成產品圖片或影片,則不需要安裝,因為它不執行生成。
執行需求
以 stdio 本機程序執行於桌面 MCP 用戶端,例如 Claude Desktop、Cursor、Windsurf 或 Continue。可透過 Smithery CLI 安裝,或以 Node.js 與 pnpm 從原始碼安裝。未宣告需要 API 金鑰、帳號或環境變數。
安裝前請注意
此伺服器被描述為唯讀、不需 API 金鑰且無配額,也不會建立或修改內容。它回傳官方連結與定價指引,依賴前請在官方網站確認目前價格與條款。未要求任何憑證或寫入操作。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Maker AI MCP,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。

其他 MCP 客戶端

參照 儲存庫 中的啟動說明。

README

Maker AI MCP Server

Maker AI - AI Product Photo, Video & Ad Generator for Ecommerce

[MCP Badge] [License: MIT] [Node] [smithery] [MCP] [Stdio Transport] [Read Only]

[Maker AI]

A Model Context Protocol server that exposes the canonical Maker AI knowledge surface — video generation workflows, pricing, FAQ, official links — to MCP-compatible AI clients such as Claude Desktop, Cursor, Windsurf, and Continue. Read-only, no API keys, no quota, ~50 ms cold start.

Official website: https://makerai.online

🎬 About Maker AI

Maker AI is an AI-powered creative studio built for ecommerce brands that need product content at scale. Users upload a product photo or paste a Shopify or Amazon store URL, and the platform generates studio-quality product images, short-form video ads, and UGC-style clips from that single input. Rather than coordinating photographers, video editors, and content creators separately, teams can produce all three content formats in one workflow. The platform draws on more than sixteen video generation models — including Sora, Kling, and Veo — selecting the appropriate model automatically based on the task. The result is a faster creative loop that lets brands test more variations without proportionally increasing production effort.

Key Features

  • Multi-format output from one upload — a single product photo or store URL produces studio photos, video ads, and UGC-style clips without separate workflows for each format.
  • 16+ video model access — the platform routes generation tasks to the most suitable model automatically, covering Sora, Kling, Veo Fast, and others without requiring manual model selection.
  • 1,000+ AI avatar library — UGC-style clips can feature realistic digital humans speaking in multiple languages including Spanish, French, German, Arabic, Russian, Korean, and Japanese, removing the need to hire or brief human creators.
  • Platform-optimized export — content is formatted with native aspect ratios and pacing for TikTok, Instagram Reels, YouTube Shorts, Amazon listings, and Shopify product pages.
  • Proven ad hook templates — a library of structured templates based on high-performing ad formats helps teams produce on-brand creative without starting from a blank slate.
  • Inspiration library — ready-made examples demonstrate what finished outputs look like across different product categories and platforms, useful for briefing or for direct adaptation.

Use Cases

  • An Amazon seller needs fresh product listing images and short video clips for a seasonal campaign but lacks an in-house studio; they paste the product URL and export platform-ready assets the same day.
  • A DTC brand running paid social wants to A/B test six ad hook variations for a new product launch without engaging an agency for each iteration.
  • An ecommerce team expanding into French and Spanish markets generates localized UGC-style videos with AI avatars speaking each language rather than coordinating separate creator shoots.
  • A Shopify store owner wants professional-looking background-swapped product photos to replace raw supplier images on their product pages.
  • A growth team wants to refresh ad creative weekly to counter fatigue without increasing the content production budget.

Who Is It For

Maker AI targets ecommerce operators who produce product content regularly and feel the friction of traditional production. The primary users are DTC brand owners, Amazon sellers, and in-house ecommerce growth teams at product-focused companies. It suits teams that run paid social campaigns, manage multiple product SKUs, or sell across several international markets — situations where the volume and variety of required content outpaces what a small team can produce through conventional means. Freelancers and small agencies managing multiple ecommerce clients will also find the multi-format workflow useful for keeping per-client production costs contained.

Tools

list_video_modes

Return the canonical list of video-generation modes the site supports. (Maker AI)

Input: no parameters. Returns: text/markdown.

get_pricing

Return the canonical pricing entry point for Maker AI.

Input: no parameters. Returns: text/markdown.

get_official_links

Return the canonical list of official links for Maker AI (website, support, docs when available).

Input: no parameters. Returns: text/markdown.

Resources

  • site://makerai/video-modes — Available video-generation modes (text-to-video, image-to-video, etc.).
  • site://makerai/pricing — Canonical pricing entry point.
  • site://makerai/faq — Short FAQ generated from public site metadata.
  • site://makerai/links — Canonical URLs to share with users.

Prompts

tell_me_about_makerai

Summarize what the site is, who it's for, and how it works. — Maker AI

try_video_mode_makerai

Pick a video-generation mode for a stated creative intent. — Maker AI

Installation

Install via Smithery

bash
npx -y @smithery/cli install makerai-mcp --client claude

(Replace claude with cursor, windsurf, or continue for those clients.)

Install from source

bash
git clone https://github.com/rocnubie/makerai-mcp.gitcd makerai-mcppnpm install

Then add to your MCP client config (claude_desktop_config.json for Claude Desktop, mcp.json for Cursor / Windsurf / Continue):

json
{  "mcpServers": {    "makerai-mcp": {      "command": "node",      "args": [        "/absolute/path/to/makerai-mcp/src/index.mjs"      ]    }  }}

Debug with MCP Inspector

bash
npx @modelcontextprotocol/inspector node src/index.mjs

Official Links

Development

bash
pnpm installpnpm start                 # run the server over stdio

License

MIT

來源:README.md,提交 8c56720

工具

0
SourceWeft 尚未在沙箱中啟動過該軟體包,因此其工具未知。

版本歷史

1
  1. v0.1.0最新Sep 16, 2026

評分

已滿足適用檢查項的 50%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通25 分

    請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。

  • 已宣告認證方式10 分

    請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。

  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分