Vadyu AI Video Ad Studio

com.vadyu由 vadyu.com 發布官方發布者v1.0.0更新於 Oct 24, 2026

Generate commercial multi-shot AI product video ads from image URLs with coherence grading.

已驗證Streamable HTTP可網頁執行商業與電商媒體與設計

概覽

AI 產生的概覽

Vadyu AI 影片廣告工作室的遠端 MCP 伺服器，可將產品照片生成多鏡頭商業影片廣告，並管理帳戶內的算圖工作。

可以做什麼
依圖片 URL 或 base64 圖片生成單鏡頭或多鏡頭產品影片廣告，可設定畫面比例、分鏡序列與變體數量，並輪詢算圖狀態取得簽章 MP4 連結與一致性評分。瀏覽支援的分鏡序列、畫面比例、音訊氛圍與導演配方，並依狀態篩選列出已生成影片。建立並自訂虛擬工作室分支，透過協作工作階段迭代角色陣容、場景區塊、品牌文案與音訊，並向上游提出或合併拉取請求。查看訂閱方案、剩餘算圖額度與生成資格，提交配方構想或意見回饋。
適用情境
當你希望助理依產品照片製作短影音廣告，或在不離開對話的情況下管理、檢視現有 Vadyu 帳戶的算圖結果、配方與工作室分支時使用。
執行需求
遠端 Streamable HTTP 端點，遠端方式無需本機安裝。需要 Vadyu 帳戶與從儀表板取得的 API 金鑰，以 bearer 權杖形式放在 Authorization 標頭中（本機 stdio 橋接方式使用 VADYU_API_KEY 環境變數並需要 Node.js）。
安裝前請注意
API 金鑰屬機密資訊，透過 Authorization 標頭傳送，請勿放入共用設定。生成會消耗與付費訂閱方案綁定的算圖額度；相關工具會建立分支、提交意見回饋以及提出或合併上游拉取請求，因而改變帳戶與社群狀態。產品圖片會傳送到 Vadyu 的伺服器。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Vadyu AI Video Ad Studio，將其新增到工作區。
  2. 連接 Authorization token 憑證。它們會被私密儲存，絕不會在公開頁面上展示。
  3. 為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/com.vadyu%2Fvadyu/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "vadyu-ai-video-ad-studio": {
      "type": "http",
      "url": "https://vadyu.com/api/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

README

Vadyu MCP Server (com.vadyu/vadyu)

Official Model Context Protocol (MCP) server for Vadyu AI Video Ad Studio — turn any product photo URL (image_url) or base64 image into commercial multi-beat video ads (9:16 TikTok/Reels, 4:5 Meta Feed, 1:1 Square, 16:9 YouTube) with automated product-label coherence grading.

Quick Setup

Option 1: Remote Streamable HTTP MCP (Cursor, Claude Code, Windsurf, VS Code)

No local installation required. Add https://vadyu.com/api/mcp directly to your MCP configuration:

json
{  "mcpServers": {    "vadyu": {      "url": "https://vadyu.com/api/mcp",      "headers": {        "Authorization": "Bearer vadyu_live_YOUR_API_KEY"      }    }  }}

Option 2: Local stdio Bridge (Claude Desktop claude_desktop_config.json)

json
{  "mcpServers": {    "vadyu": {      "command": "sh",      "args": ["-c", "curl -fsSL https://vadyu.com/mcp/vadyu-mcp.mjs | node"],      "env": {        "VADYU_API_KEY": "vadyu_live_YOUR_API_KEY"      }    }  }}

Or clone this repository and run node vadyu-mcp.mjs with VADYU_API_KEY set in your environment.

Available MCP Tools

Tool NameDescription
vadyu_generate_video_adGenerate a single (5s) or multi-beat (10s–20s) commercial product video ad from image_url or image_base64, prompt, format (9:16, 1:1, 16:9, 4:5), sequence (problem-solution, ugc-testimonial, product-feature, unboxing, single), and variants (1–3).
vadyu_get_video_statusPoll rendering progress (processing, done, failed), beat completion, coherence_score (0–100), and retrieve the signed MP4 video_url.
vadyu_list_videosList generated video ads in the authenticated account with status filtering and pagination.
vadyu_get_account_quotaCheck active subscription tier, remaining monthly render credits, and generation eligibility.
vadyu_list_sequences_and_formatsInspect all supported multi-beat ad storyboard templates and aspect ratio formats.

License

MIT — see LICENSE.

來源：README.md，提交 5d1b5d8

工具

12

vadyu_generate_video_ad

Generate a commercial AI product video ad from a product photo URL (image_url) or base64 image (image_base64). Supports both API v2 Director Recipes (nyc_luxury, minimal_cinema, dtc_story, or custom blocks[] combining AI motion scenes, deterministic brand messaging typography cards, synthesized background audio scores, and stark #000000 black-screen brand logo slates) and multi-beat storyboards (problem-solution, ugc-testimonial, product-feature, unboxing, single) in 9:16, 1:1, 16:9, or 4:5. Deterministic text_card and logo_outro blocks consume 0 AI render credits.

輸入參數blocksformatpromptrecipefork_idlogo_urlsequencevariantsimage_urllogo_textaudio_moodbrand_text另有 3 個

vadyu_list_recipes

List all API v2 Composable Director Recipes (nyc_luxury, minimal_cinema, dtc_story), custom block schemas (ai_scene, text_card, logo_outro), synthesized audio moods (nyc_dusk, luxury_ambient, modern_pulse, none), credit rules, and community-submitted recipe blueprints.

無需輸入參數。

vadyu_submit_recipe_feedback

Submit a new custom ad recipe idea, multi-scene storyline blueprint, or product feedback to Vadyu's creative engineering team.

輸入參數titlelogo_textstoryline必填audio_moodbrand_text

vadyu_get_video_status

Poll the rendering status, beat progress, recipe block timeline, coherence score, and signed MP4 download URL (video_url) of a generated Vadyu video ad by its numeric video_id.

輸入參數video_id必填

vadyu_list_videos

List generated video ads in the authenticated Vadyu account, with optional status filtering ('done', 'processing', 'failed') and pagination.

輸入參數pagelimitstatus

vadyu_get_account_quota

Check the authenticated user's active Vadyu subscription plan, remaining monthly render credits, total render quota, and generation eligibility.

無需輸入參數。

vadyu_list_sequences_and_formats

List all supported Vadyu multi-beat ad sequences (storyboards), API v2 Director Recipes, audio moods, and aspect ratio formats along with beat counts, durations, and prompt best practices.

無需輸入參數。

vadyu_list_studio_forks

List all API v3 Virtual Studio Forks (your personal forks, community forks, upstream main blueprint, and starter fork templates like 'nyc_luxury_cameo' and 'director_cast_storyline').

無需輸入參數。

vadyu_create_studio_fork

Create a new API v3 Virtual Studio Fork (similar to a GitHub repo fork) from upstream 'main', a starter template ('nyc_luxury_cameo' or 'director_cast_storyline'), or an existing parent_fork_id. Optionally pass initial_prompt to let the Interactive Co-Builder customize the cast, timeline blocks, brand messaging card, black-screen logo outro, and audio score on creation.

輸入參數titledescriptiontemplate_idinitial_promptparent_fork_id

vadyu_collaborate_on_fork

Interactive Co-Builder session turn on an API v3 Studio Fork. Send natural-language creative direction (message) or a structured blueprint patch to evolve the fork's character cast (roles, wardrobe, visual continuity lock), composable scene/text/logo blocks, brand copy, and audio score. Returns the updated blueprint, commit count, and Git-style diff against upstream 'main'.

輸入參數patchfork_id必填message

vadyu_promote_studio_fork

Open an upstream Pull Request ('pr_open') against Vadyu's core 'main' studio pipeline so a high-performing API v3 Studio Fork can be reviewed and merged into the official product.

輸入參數fork_id必填pr_notespr_title

vadyu_merge_studio_fork

Merge an API v3 Studio Fork ('pr_open' or 'active') into the upstream Vadyu 'main' community catalog and unlock +10 bonus render credits.

輸入參數fork_id必填reviewer_notes

版本歷史

1
  1. v1.0.0最新Oct 24, 2026

評分

已滿足適用檢查項的 100%

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 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分

其他 Vadyu 整合

Xmorf

由 GitHub 帳號 crawde 發布

一個本機 MCP 伺服器，讓助理透過 xmorf AI 影像 API 編輯與生成圖片，並列出可用模型。

STDIO僅桌面
媒體與設計尚未驗證Oct 24, 2026

Chartforge

由 GitHub 帳號 crawde 發布

ChartForge MCP 伺服器，讓助手在 Claude Desktop 中依自然語言描述產生並調整圖表與示意圖。

STDIO僅桌面
資料與分析尚未驗證Oct 24, 2026

Chartforge

com.chartforgeai

Chartforge 是本地 MCP 伺服器，讓助理依自然語言描述產生並調整圖表與示意圖。

STDIO僅桌面
資料與分析尚未驗證Oct 24, 2026