kevinten-ai/mcp-video-gen

このページは AI により自動翻訳されています。技術的な詳細は原文をご確認ください。原文を見る

15 stars 8 forks 品質 82 トレンド 29MIT

MCP server for AI video generation with multiple providers. Supports CogVideoX (free unlimited), Alibaba Wan, Kling AI, SiliconFlow, Vidu, and MiniMax Hailuo.

概要

Multi-provider AI video, speech, music & transcription MCP server. 7 video providers + image-to-video + TTS + music + STT — one unified interface. Works with Claude Code, Claude Desktop, Cursor, and any MCP-compatible client. - — Volcengine Ark Seedance, DashScope/Wan, Kling, SiliconFlow, Vidu, MiniMax, Google Veo (2/3/3.1) - — generate videos from reference images (Veo) - — text-to-speech via MiniMax (+ Google Chirp 3 HD with ADC) - — MiniMax Music + (instrumental, ~33s, GCP credits) - — transcribe audio with word-level timestamps via Google Chirp 2 (for subtitle generation) - — Volcengine Ark Seedance is available via ARK_API_KEY / ARK_VIDEO_* - — choose the best provider per request via provider parameter - — generated videos/audio saved to local disk automatically All video providers use an : submit a generation request, get a task ID, then poll until complete.

README

以下は原文 README の抜粋です。原文を見る。

mcp-video-gen

中文文档

Features

7 video providers — Volcengine Ark Seedance, DashScope/Wan, Kling, SiliconFlow, Vidu, MiniMax, Google Veo (2/3/3.1)
Image-to-video — generate videos from reference images (Veo)
TTS — text-to-speech via MiniMax (+ Google Chirp 3 HD with ADC)
Music generation — MiniMax Music + Google Lyria (instrumental, ~33s, GCP credits)
Speech-to-text — transcribe audio with word-level timestamps via Google Chirp 2 (for subtitle generation)
Ark migration ready — Volcengine Ark Seedance is available via ARK_API_KEY / ARK_VIDEO_*
Provider switching — choose the best provider per request via provider parameter
Auto-download — generated videos/audio saved to local disk automatically

Architecture

How It Works

User Prompt → AI Assistant (Claude / Cursor) → MCP Server → Provider API
                                                    ↓
                                        generate_video() → task_id
                                        query_video_status(task_id) → download to disk

All video providers use an async pattern: submit a generation request, get a task ID, then poll until complete. The MCP server handles this transparently — the AI assistant calls generate_video, then query_video_status in a loop until the video is ready.

Supported Providers

Video Providers

Provider	Model	Free Tier	Quality	Duration	Best for
Volcengine Ark Seedance	doubao-seedance-2.0	Paid video API	720p+	5-10s	Ark migration, Doubao/Seedance workflows
DashScope / Wan (通义万相)	wan2.6-t2v	50s free (90 days)	Up to 1080P	5-10s	High quality, Chinese content
Kling AI (可灵)	kling-v2-master	66 credits/day (web only)	720p	5-10s	Good quality, daily free credits
SiliconFlow (硅基流动)	Wan2.1-T2V-14B	$1 signup bonus	720p	varies	Quick testing

GitHub で README 全文を見る

インストール

npx @modelcontextprotocol/inspector uv --directory . run --extra gcp video-gen

MCP 初心者？mcpskill.org のガイドから始めましょう →

設定

{
  "mcpServers": {
    "mcp-video-gen": {
      "command": "uv",
      "args": ["--directory", "/path/to/mcp-video-gen", "run", "--extra", "gcp", "video-gen"],
      "env": {
        "ARK_API_KEY": "your_key",
        "ARK_VIDEO_MODEL": "doubao-seedance-2-0-fast-260128",
        "GCP_PROJECT_ID": "your-project-id",
        "GEMINI_API_KEY": "your_gcp_api_key"
      }
    }
  }
}