広告掲載
MCP.so
ログイン

VicSee MCP Server

@vicseeai

リポジトリ

基本情報

カテゴリ

メディアとデザイン

トランスポート

stdio

作者

vicseeai

投稿者

JZ

VicSee MCP Server について

Generate, edit, and upscale AI video & images from any agent — VicSee as a set of MCP tools. Multi-model (Seedance, Veo, Kling, FLUX, Nano Banana), text or image to video or image, with async task polling. Six tools: list models, generate, poll task, upscale image, upscale video,

#ai#video-generation#image-generation#media#text-to-video#image-to-video#text-to-image#upscaling

VicSee MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "vicsee": {
      "command": "npx",
      "args": [
        "-y",
        "@vicsee/mcp-server"
      ],
      "env": {
        "VICSEE_API_KEY": "sk-your-key-here"
      }
    }
  }
}

VicSee MCP Server のツール

7

List available VicSee models with their capabilities and credit costs. Call this first to find a model id to pass to vicsee_generate. Optionally filter by media type.

Create an AI image or video with VicSee. Generation is ASYNCHRONOUS: this returns a task `id` immediately, then poll `vicsee_get_task` with that id until status is "completed" (the result URL appears in result.url) or "failed". Use vicsee_list_models to pick a `model` and see its valid options. For image-to-video / image-to-image, pass source images in `image_urls`. For reference-to-video models (e.g. "seedance-2-5-reference-to-video"), pass references in reference_image_urls / reference_video_urls / reference_audio_urls and refer to them positionally in the prompt as @Image1, @Image2, … For native 2K output at the best value per second use the "minimax-h3-*" models (MiniMax H3, also called Hailuo 03): 4-15s, 768P/2K, always-on stereo audio, billed per second (25 credits/s at 768P, 40 at 2K). Note "minimax-h3-image-to-video" takes the first frame in image_urls[0] and an optional last frame in image_urls[1], and has NO aspect_ratio parameter — the ratio follows the frames; "minimax-h3-reference-to-video" requires at least one image OR video reference (audio alone is rejected) and accepts at most 5 reference images. For clips longer than 15 seconds use the "seedance-2-5-*" models, which generate up to 30 seconds (480p/720p only, no 1080p or 4K); the "seedance-2-0-*" models cap at 15 seconds but add 1080p and 4K. Note that supplying a video reference switches billing to per-second across input + output, so a long reference clip costs considerably more than the duration table suggests — check credits in vicsee_list_models before generating. IMAGE inputs (image_urls, reference_image_urls) may be a public https URL, a local file path (this server reads and base64-encodes it for you), or a base64 data URI. VIDEO/AUDIO inputs (reference_video_urls, reference_audio_urls) must be public https URLs. For video-edit models (e.g. "happyhorse-video-edit"), pass the source clip in video_url and optionally set audio_setting ("auto" or "origin"). Input images must have an aspect ratio between 0.4 and 2.5 (width÷height) and at most 36MP — wide-strip composites (e.g. 3:1) are rejected; use a 2×2 grid layout instead. On "failed" tasks, read error.key and error.message from vicsee_get_task — they state the actual reason (do not guess).

Poll a generation or upscale task by its id. status is one of "pending" | "processing" | "queued" | "completed" | "failed". When "completed", the media URL is in result.url (videos/images) or result.songs (music). When "failed", details are in error. Poll every few seconds until completed or failed.

Upscale a publicly accessible image (JPEG/PNG/WebP). Asynchronous: returns a task id — poll vicsee_get_task until completed. upscale_factor defaults to "2" (max "4"). Credits are tiered by OUTPUT size (input megapixels × factor²): ≤24MP = 20, ≤48MP = 40, ≤96MP = 80; outputs above 96MP are rejected.

Upscale a publicly accessible video (MP4/MOV/MKV, up to 60s). Asynchronous: returns a task id — poll vicsee_get_task until completed. upscale_factor defaults to "2".

Get the current VicSee credit balance for the configured API key.

Upload a LOCAL file (image, video, or audio) from this machine and get back a public https URL. Use the returned url as an input for vicsee_generate — e.g. drop it into reference_image_urls for a reference-to-video storyboard, or image_urls for image-to-video. PREFER this over inline base64 for references: large base64 strings get truncated in tool-call output and the model rejects them. The file uploads directly to storage; only its public URL comes back.

概要

What is VicSee MCP Server?

VicSee MCP Server provides tools for AI video and image generation, editing, and upscaling from any MCP-compatible client. It connects agents to the VicSee API, supporting models like Seedance, Veo, Kling, FLUX, and more. It is designed for developers and AI agents using Hermes Agent, Claude, Cursor, OpenClaw, or any MCP client.

How to use VicSee MCP Server?

Obtain an API key from VicSee (requires a paid plan or credit pack), then add the server to your MCP client’s configuration with the key in the VICSEE_API_KEY environment variable. Use tools like vicsee_generate to start a task, then poll with vicsee_get_task to retrieve the finished media URL.

Key features of VicSee MCP Server

  • List available models and their credit costs
  • Generate video or image from text or image
  • Poll tasks until completion and retrieve media URL
  • Upscale both images and videos
  • Check your remaining credit balance
  • Asynchronous generation with task-based polling

Use cases of VicSee MCP Server

  • Agents creating short videos from text prompts
  • Integrating AI image generation into workflows
  • Upscaling user‑uploaded or generated media
  • Automating batch generation with model selection
  • Building interactive creative tools that use MCP

よくある質問

1

What tools does VicSee MCP Server provide?

It provides six tools: `vicsee_list_models`, `vicsee_generate`, `vicsee_get_task`, `vicsee_upscale_image`, `vicsee_upscale_video`, and `vicsee_get_credits`.

2

How does video/image generation work?

Generation is asynchronous: `vicsee_generate` returns a task `id` immediately; your agent polls `vicsee_get_task` until `status` is `completed`, then reads the media URL from `result.url`.

3

How do I get an API key?

Get your API key at vicsee.com → Settings → API. Keys start with `sk-`. API access requires a paid plan or credit pack.

4

What models are available?

Available models include Seedance, Veo, Kling, FLUX, Nano Banana, and others. Use `vicsee_list_models` to see the full list and their credit costs.

5

How is pricing handled?

Each generation costs credits. Check per‑model costs with `vicsee_list_models` and your balance with `vicsee_get_credits`.

コメント

「メディアとデザイン」の他のコンテンツ

F

FrontRowTickets.com MCP Server

Live FrontRowTickets.com ticket inventory for AI agents: search, availability, pricing, deals.

CoDesign

IMG.LY

Give your AI agent a real design engine. Create, edit and export real, editable designs from Claude Code, Codex, Cursor and more.

Notch

Notch

Create finished video ads from chat. Give Notch a brief or product URL — it loads your brand context, writes the script, and produces the finished ad: avatar, scenes, voiceover, captions. Built for performance marketers,

Designesy

LE-VAI

Design quality gate for AI-generated UI. Scores any live URL against a published contract of deterministic checks, with an A–F grade, a per-check breakdown and AI-slop pattern findings; validates DTCG token files and Lot

SnapDub

SnapDub

Turn long videos into captioned vertical clips for TikTok, Reels and Shorts from Claude, ChatGPT, Cursor or any MCP client. Paste a YouTube, Twitch, Kick, Rumble or Zoom link and get clips with titles, virality scores, d

広告掲載