Vadyu AI Video Ad Studio

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

我该使用它吗

质量与安全性

A
描述质量
98%
模式完整度
74%
命名质量
78%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

发现(1)

  • LOWTool 'vadyu_list_sequences_and_formats' name length outside 3-30 range在 vadyu_list_sequences_and_formats 中

基于对工具定义和协议合规性的自动分析。

上下文开销

~3,232token 数(工具定义)
~2.3 KB典型响应大小
对注意力有显著影响(占 128k 上下文窗口的 2.53%)

这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高,可用于其他任务的注意力就越少。

安装

一键安装

将以下内容添加到你的 `claude_desktop_config.json` 文件中:

{
  "mcpServers": {
    "vadyu": {
      "url": "https://vadyu.com/api/mcp"
    }
  }
}

远程端点

https://vadyu.com/api/mcpstreamable-http

它能做什么

工具清单

工具(12)

🟢 只读🟡 写入🔴 删除⚪ 未知
⚪vadyu_generate_video_ad(image_url, image_base64, prompt, fork_id, recipe, ...)

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 (50 presets such as nyc_luxury, minimal_cinema, dtc_story and editorial_flagship, 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.

输入模式

{
  "type": "object",
  "properties": {
    "image_url": {
      "type": "string",
      "description": "Public HTTP/HTTPS URL of the source product photo (JPG, PNG, or WebP)."
    },
    "image_base64": {
      "type": "string",
      "description": "Base64-encoded product image data (alternative to image_url)."
    },
    "prompt": {
      "type": "string",
      "description": "Optional camera motion and lighting direction (e.g., 'Slow 360 studio turntable rotation with warm golden rim lighting, crisp product label')."
    },
    "fork_id": {
      "type": "string",
      "description": "Optional API v3 Virtual Studio Fork ID (e.g., 'fork_...') created via vadyu_create_studio_fork. Renders the ad using the fork's custom character cast, visual continuity locks, composable blocks, brand intertitles, black-screen logo outro, and synthesized audio."
    },
    "recipe": {
      "type": "string",
      "enum": [
        "nyc_luxury",
        "minimal_cinema",
        "dtc_story",
        "editorial_flagship",
        "brand_sting_bumper",
        "museum_plinth",
        "silent_manifesto",
        "clinical_clean",
        "proof_first_split",
        "offer_first_anchor",
        "countdown_drop",
        "three_reasons",
        "pov_it_arrived",
        "grand_campaign_12",
        "founders_letter",
        "craft_documentary",
        "film_noir",
        "levitation_dream",
        "retro_rewind",
        "unboxing_asmr",
        "rainy_paris_cafe",
        "night_drive_neon",
        "desert_light",
        "greenhouse_botanical",
        "holiday_gift",
        "poolside_summer",
        "cabin_cozy",
        "morning_ritual",
        "locker_room_energy",
        "spec_sheet",
        "flat_lay_kitchen",
        "pet_companion",
        "street_session",
        "desk_setup",
        "train_window_passage",
        "day_with_five_hours",
        "after_dark_montage",
        "hotel_edit_offer",
        "snow_silent_film",
        "cup_holder_deadpan",
        "myth_fact_label",
        "first_light_bumper",
        "six_atelier_chapters",
        "quiet_nursery_ritual",
        "two_voices_dialogue",
        "four_elements_proof",
        "ferry_deck_wind",
        "offer_sandwich_sprint",
        "eclipse_teaser_drop",
        "split_blink_bumper"
      ],
      "description": "Optional API v2 Director Recipe preset id. Signature presets: 'nyc_luxury' (NYC cab cameo + brand card + black logo, 14.5s, 2 renders), 'minimal_cinema' (hero + brand card + logo, 9.5s, 1 render), 'dtc_story' (creator hook + value card + lifestyle + logo, 14.5s, 2 renders), 'editorial_flagship' (7 cuts, 20.7s, 2 renders). Recipe Foundry presets (call vadyu_list_recipes for timelines, tags and themes): 'brand_sting_bumper', 'museum_plinth', 'silent_manifesto', 'clinical_clean', 'proof_first_split', 'offer_first_anchor', 'countdown_drop', 'three_reasons', 'pov_it_arrived', 'grand_campaign_12', 'founders_letter', 'craft_documentary', 'film_noir', 'levitation_dream', 'retro_rewind', 'unboxing_asmr', 'rainy_paris_cafe', 'night_drive_neon', 'desert_light', 'greenhouse_botanical', 'holiday_gift', 'poolside_summer', 'cabin_cozy', 'morning_ritual', 'locker_room_energy', 'spec_sheet', 'flat_lay_kitchen', 'pet_companion', 'street_session', 'desk_setup', 'train_window_passage', 'day_with_five_hours', 'after_dark_montage', 'hotel_edit_offer', 'snow_silent_film', 'cup_holder_deadpan', 'myth_fact_label', 'first_light_bumper', 'six_atelier_chapters', 'quiet_nursery_ritual', 'two_voices_dialogue', 'four_elements_proof', 'ferry_deck_wind', 'offer_sandwich_sprint', 'eclipse_teaser_drop', 'split_blink_bumper'."
    },
    "brand_text": {
      "type": "string",
      "description": "Editorial brand headline rendered on the deterministic text_card intertitle (e.g., 'TIMELESS IN MOTION'). Costs 0 AI render credits."
    },
    "brand_subtext": {
      "type": "string",
      "description": "Optional secondary subtitle rendered beneath brand_text on text_card blocks (e.g., 'NEW YORK · AUTUMN / WINTER')."
    },
    "logo_text": {
      "type": "string",
      "description": "Brand wordmark rendered on the final stark #000000 black-screen logo_outro slate (e.g., 'CHANEL'). Costs 0 AI render credits."
    },
    "logo_url": {
      "type": "string",
      "description": "Optional public HTTP/HTTPS URL of a PNG/SVG/WebP brand logo to center on the stark black-screen logo_outro slate."
    },
    "audio_mood": {
      "type": "string",
      "enum": [
        "nyc_dusk",
        "luxury_ambient",
        "modern_pulse",
        "none"
      ],
      "description": "Synthesized background audio score mixed into Director Recipes: 'nyc_dusk', 'luxury_ambient', 'modern_pulse', or 'none'."
    },
    "scene_prompts": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Optional array of custom motion prompts corresponding to each ai_scene block in a recipe."
    },
    "blocks": {
      "type": "array",
      "description": "Optional custom API v2 composable timeline (up to 8 blocks; must include at least 1 'ai_scene' block). Deterministic 'text_card' and 'logo_outro' blocks cost 0 render credits.",
      "items": {
        "type": "object",
        "properties": {
          "type": {
            "type": "string",
            "enum": [
              "ai_scene",
              "text_card",
              "logo_outro"
            ]
          },
          "label": {
            "type": "string"
          },
          "prompt": {
            "type": "string",
            "description": "Camera/scene motion prompt (for ai_scene blocks)."
          },
          "headline": {
            "type": "string",
            "description": "Headline text (for text_card blocks)."
          },
          "subheadline": {
            "type": "string",
            "description": "Subheadline text (for text_card blocks)."
          },
          "logo_text": {
            "type": "string",
            "description": "Brand logo text (for logo_outro blocks)."
          },
          "duration_sec": {
            "type": "number",
            "description": "Duration in seconds (1-5s for text_card/logo_outro)."
          }
        },
        "required": [
          "type"
        ]
      }
    },
    "format": {
      "type": "string",
      "enum": [
        "9:16",
        "1:1",
        "16:9",
        "4:5"
      ],
      "default": "9:16",
      "description": "Aspect ratio: '9:16' (Reels/TikTok/Shorts), '1:1' (Square), '16:9' (YouTube/Web), '4:5' (Meta Feed)."
    },
    "sequence": {
      "type": "string",
      "enum": [
        "problem-solution",
        "ugc-testimonial",
        "product-feature",
        "unboxing",
        "single"
      ],
      "default": "problem-solution",
      "description": "Standard storyboard template (used when 'recipe' and 'blocks' are omitted): 'problem-solution' (4 beats, ~20s), 'ugc-testimonial' (4 beats, ~20s), 'product-feature' (3 beats, ~15s), 'unboxing' (3 beats, ~15s), or 'single' (1 beat, 5s)."
    },
    "variants": {
      "type": "integer",
      "minimum": 1,
      "maximum": 3,
      "default": 1,
      "description": "Number of parallel creative variants to render (1 to 3)."
    }
  }
}
🟢vadyu_list_recipes

List all 50 API v2 Composable Director Recipes (signature presets plus the Recipe Foundry catalog, each with collection, tags and theme), custom block schemas (ai_scene, text_card, logo_outro, ken_burns_still, flash_cut_intro, cta_endcard, split_before_after), synthesized audio moods (nyc_dusk, luxury_ambient, modern_pulse, none), credit rules, and community-submitted recipe blueprints.

输入模式

{
  "type": "object",
  "properties": {}
}
🟡vadyu_submit_recipe_feedback(title, storyline, brand_text, logo_text, audio_mood)

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

输入模式

{
  "type": "object",
  "properties": {
    "title": {
      "type": "string",
      "description": "Short name for the proposed recipe (e.g., 'Parisian Cafe Espresso Reveal')."
    },
    "storyline": {
      "type": "string",
      "description": "Scene-by-scene storyline description (e.g., 'Scene 1: Steam rising off product -> Text card: MORNING RITUAL -> Scene 2: Woman at cafe table -> Black screen logo + warm jazz chord')."
    },
    "brand_text": {
      "type": "string",
      "description": "Optional example brand messaging intertitle text."
    },
    "logo_text": {
      "type": "string",
      "description": "Optional example brand logo slate text."
    },
    "audio_mood": {
      "type": "string",
      "enum": [
        "nyc_dusk",
        "luxury_ambient",
        "modern_pulse",
        "none"
      ],
      "description": "Preferred background audio mood."
    }
  },
  "required": [
    "storyline"
  ]
}
🟢vadyu_get_video_status(video_id)

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.

输入模式

{
  "type": "object",
  "properties": {
    "video_id": {
      "type": "integer",
      "description": "Numeric video ID returned by vadyu_generate_video_ad."
    }
  },
  "required": [
    "video_id"
  ]
}
🟢vadyu_list_videos(status, limit, page)

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

输入模式

{
  "type": "object",
  "properties": {
    "status": {
      "type": "string",
      "enum": [
        "done",
        "processing",
        "failed"
      ],
      "description": "Optional filter by rendering status."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50,
      "default": 10,
      "description": "Number of videos to return per page (1-50, default 10)."
    },
    "page": {
      "type": "integer",
      "minimum": 1,
      "default": 1,
      "description": "Page number (1-indexed)."
    }
  }
}
🟢vadyu_get_account_quota

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

输入模式

{
  "type": "object",
  "properties": {}
}
🟢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.

输入模式

{
  "type": "object",
  "properties": {}
}
🟢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').

输入模式

{
  "type": "object",
  "properties": {}
}
🟡vadyu_create_studio_fork(title, description, template_id, parent_fork_id, initial_prompt)

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.

输入模式

{
  "type": "object",
  "properties": {
    "title": {
      "type": "string",
      "description": "Human-readable name for the Studio Fork (e.g., 'NYC Dusk Cab Chanel Fork')."
    },
    "description": {
      "type": "string",
      "description": "Short description of the fork's creative direction or campaign goal."
    },
    "template_id": {
      "type": "string",
      "enum": [
        "nyc_luxury_cameo",
        "director_cast_storyline"
      ],
      "description": "Optional starter fork template: 'nyc_luxury_cameo' (Motion scene → Brand message text card → Woman hailing a cab in NYC with Chanel bag glimpse → Stark black screen brand logo + NYC dusk audio) or 'director_cast_storyline' (Movie Director multi-character casting with locked visual continuity)."
    },
    "parent_fork_id": {
      "type": "string",
      "description": "Optional parent fork ID to branch from (defaults to 'main')."
    },
    "initial_prompt": {
      "type": "string",
      "description": "Optional natural-language instruction for the Interactive Co-Builder to immediately customize the fork's cast, scenes, brand text cards, black-screen logo slate, or audio mood."
    }
  }
}
🟡vadyu_collaborate_on_fork(fork_id, message, patch)

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'.

输入模式

{
  "type": "object",
  "properties": {
    "fork_id": {
      "type": "string",
      "description": "Target Studio Fork ID (e.g., 'fork_...')."
    },
    "message": {
      "type": "string",
      "description": "Natural-language instruction to the Vadyu Co-Builder (e.g., 'Cast a woman in a camel coat hailing a yellow cab in NYC with a glimpse of her Chanel bag, insert brand text TIMELESS IN MOTION, and cut to a black screen with logo CHANEL')."
    },
    "patch": {
      "type": "object",
      "description": "Optional structured partial patch for the StudioForkBlueprint (cast, blocks, brand_copy, audio, camera_style, lighting_rig)."
    }
  },
  "required": [
    "fork_id"
  ]
}
⚪vadyu_promote_studio_fork(fork_id, pr_title, pr_notes)

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.

输入模式

{
  "type": "object",
  "properties": {
    "fork_id": {
      "type": "string",
      "description": "Studio Fork ID to promote (e.g., 'fork_...')."
    },
    "pr_title": {
      "type": "string",
      "description": "Title for the upstream Pull Request."
    },
    "pr_notes": {
      "type": "string",
      "description": "Summary of why this fork's storyline, cast, or recipe architecture performs well."
    }
  },
  "required": [
    "fork_id"
  ]
}
⚪vadyu_merge_studio_fork(fork_id, reviewer_notes)

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

输入模式

{
  "type": "object",
  "properties": {
    "fork_id": {
      "type": "string",
      "description": "Studio Fork ID to merge into upstream main (e.g., 'fork_...')."
    },
    "reviewer_notes": {
      "type": "string",
      "description": "Optional merge notes."
    }
  },
  "required": [
    "fork_id"
  ]
}

社区

评价此服务器

证据

最近观测

已验证未记录版本12 个工具