MCP.so
ログイン
S

Short Video Agent Kit MCP Server

@davidmosiah

基本情報

カテゴリ

AI とエージェント

トランスポート

stdio

作者

davidmosiah

投稿者

David Batista

Short Video Agent Kit MCP Server について

概要はまだありません

Short Video Agent Kit 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": {
    "short-video": {
      "command": "npx",
      "args": [
        "-y",
        "short-video-agent-kit"
      ]
    }
  }
}

Short Video Agent Kit MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。

概要

What is Short Video Agent Kit?

A provider-neutral short-form AI video toolkit for agents. It gives Codex, Claude, Cursor, Hermes, OpenClaw and other MCP clients a single interface for building dry-run payloads and, when explicitly enabled, generating vertical video through Sora/OpenAI, Gemini Veo, xAI/Grok and Seedance/PiAPI-style providers. It is designed for anyone building agent workflows that need safe, credit-free prompt-to-video payload validation before optional paid generation.

How to use Short Video Agent Kit?

Install globally via npm (npm install -g short-video-agent-kit) or run directly with npx. Use the CLI commands doctor, generate, payload, manifest, privacy-audit to inspect providers, build plans, and generate video. Dry-run is the default; pass --live or set SHORT_VIDEO_DRY_RUN=false to enable paid provider calls. The package also ships as an MCP server (short-video-mcp) supporting stdio and HTTP transports. Configure provider API keys in a .env file.

Key features of Short Video Agent Kit

  • Provider-neutral interface supporting OpenAI Sora, Gemini Veo, xAI/Grok, and Seedance.
  • Dry-run by default — returns the exact payload plan without spending credits.
  • API keys are detected but never returned by any tool.
  • Paid generation requires explicit opt-in via --live or environment variable.
  • Built-in privacy audit tool for prompt and output boundaries.
  • Outputs are written to user-controlled local paths.

Use cases of Short Video Agent Kit

  • Building and validating video payloads across multiple AI video providers without spending credits.
  • Comparing provider-specific parameter shapes for the same prompt before committing to one.
  • Safely integrating short-form video generation into agent workflows with dry-run safety.
  • Generating vertical short-form teasers and product videos through a single agent interface.

よくある質問

1

Which video providers are supported?

OpenAI Sora (`openai_sora`), Gemini Veo (`gemini_veo`), xAI/Grok (`xai_grok`), and Seedance/PiAPI (`seedance_piapi`).

2

Is an API key required to try it?

No. Generation is dry-run by default, so the kit returns the exact payload plan without making any provider call or spending credits.

3

How do I enable actual paid generation?

Pass the `--live` flag to the CLI, set `live=true` in the MCP tool call, or set the environment variable `SHORT_VIDEO_DRY_RUN=false`.

4

How are API keys handled?

Keys are detected from environment variables (or a `.env` file) and checked for readiness via `short-video-agent-kit doctor`, but they are never printed or returned by any tool.

5

What transports does the MCP server support?

The MCP server (`short-video-mcp`) uses stdio by default. Set `SHORT_VIDEO_MCP_TRANSPORT=http` to enable HTTP transport.

コメント

「AI とエージェント」の他のコンテンツ