ssemble-mcp-server

ssemble-mcp-server

Create AI-powered short-form video clips from YouTube videos using any AI assistant. 9 tools for creating shorts, browsing caption templates, music, gameplay overlays, and meme hooks.

Category
访问服务器

README

Ssemble MCP Server

MCP server for Ssemble AI Clipping — create viral short-form videos from any AI assistant.

Works with Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and any MCP-compatible client.

What it does

This MCP server lets AI assistants create short-form video clips from YouTube videos using Ssemble's AI clipping engine. The AI can:

  • Create shorts from YouTube URLs or uploaded files
  • Browse assets — caption templates, background music, gameplay overlays, meme hooks
  • Track processing — check progress and retrieve completed clips
  • Manage requests — list history, get results, delete old requests

Prerequisites

  • Ssemble account with an active subscription
  • API key (get it from Settings → API Keys in the Ssemble dashboard)
  • Node.js >= 18

Quick Start

Claude Desktop

Edit your config file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "ssemble": {
      "command": "npx",
      "args": ["@ssemble/mcp-server"],
      "env": {
        "SSEMBLE_API_KEY": "sk_ssemble_your_key_here"
      }
    }
  }
}

Restart Claude Desktop after saving.

Claude Code

claude mcp add ssemble -- npx @ssemble/mcp-server

Then set the environment variable:

export SSEMBLE_API_KEY="sk_ssemble_your_key_here"

Cursor / VS Code / Windsurf

Add to your MCP settings:

{
  "mcpServers": {
    "ssemble": {
      "command": "npx",
      "args": ["@ssemble/mcp-server"],
      "env": {
        "SSEMBLE_API_KEY": "sk_ssemble_your_key_here"
      }
    }
  }
}

Available Tools

Tool Description
create_short Create AI-generated short clips from a video. Returns request ID instantly.
get_status Check processing progress (0-100%) and current step
get_shorts Retrieve completed clips with video URLs, titles, viral scores
list_requests List all your requests with pagination and status filtering
delete_request Permanently delete a request and its videos
list_templates Browse caption style templates
list_music Browse background music tracks
list_game_videos Browse gameplay overlay videos
list_meme_hooks Browse meme hook attention-grabber clips

How Processing Works

Video processing takes 5-30 minutes. The workflow is:

  1. create_short — submits the job and returns instantly with a request ID
  2. get_status — check progress anytime (queued → processing → completed)
  3. get_shorts — retrieve the generated clips when done

Usage Examples

Create shorts from a YouTube video:

"Create shorts from https://youtube.com/watch?v=abc123, use the first 10 minutes with chill background music"

Browse available assets:

"Show me all caption templates" / "What background music is available?"

Check progress:

"What's the status of my video request?"

Get results:

"Show me the clips for request 507f1f77bcf86cd799439011, sorted by viral score"

Environment Variables

Variable Required Description
SSEMBLE_API_KEY Yes Your Ssemble API key (starts with sk_ssemble_)
SSEMBLE_API_BASE_URL No Override API base URL (default: https://aiclipping.ssemble.com/api/v1)

Development

git clone https://gitlab.com/vlogr/ssemble-mcp-server.git
cd ssemble-mcp-server
npm install
SSEMBLE_API_KEY=sk_ssemble_your_key npm start

License

MIT

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选