PlayVideo MCP Server
Enables AI assistants to manage videos on PlayVideo, including collections, videos, webhooks, embed settings, API keys, and account management.
README
PlayVideo MCP Server
Model Context Protocol (MCP) server for PlayVideo API. Enables AI assistants like Claude to manage your videos directly.
What is MCP?
Model Context Protocol is an open protocol that allows AI assistants to interact with external tools and data sources. This MCP server lets Claude (and other MCP-compatible assistants) manage your PlayVideo videos.
Features
- Collections - List/create/delete collections
- Videos - List videos, get details, delete
- Webhooks - Create, test, update, and manage webhooks
- Embed settings - Read/update player settings and sign embeds
- API keys - List/create/delete API keys
- Account - Read/update account settings
- Usage - Monitor plan limits and quotas
- Upload instructions - Get curl/SDK commands for uploading
Installation
For Claude Desktop
- Install the MCP server globally:
npm install -g @playvideo/playvideo-mcp
Or run without installing:
npx @playvideo/playvideo-mcp
- Add to your Claude Desktop config (
~/Library/Application Support/Claude/claude_desktop_config.jsonon macOS):
{
"mcpServers": {
"playvideo": {
"command": "playvideo-mcp",
"env": {
"PLAYVIDEO_API_KEY": "play_live_your_api_key"
}
}
}
}
- Restart Claude Desktop
For Development
cd mcp
npm install
npm run build
Run locally:
PLAYVIDEO_API_KEY=play_live_xxx npm start
Usage Examples
Once configured, you can ask Claude things like:
- "List my video collections"
- "Create a new collection called 'Tutorials'"
- "Show me all completed videos"
- "Create a webhook for video.completed"
- "Update embed settings to autoplay and muted"
- "Generate a signed embed for video xyz123"
- "Create a new API key for production"
- "What's my current usage?"
- "Delete the video with ID xyz123"
- "How do I upload a video to the 'demos' collection?"
Available Tools
| Tool | Description |
|---|---|
list_collections |
List all video collections |
create_collection |
Create a new collection |
delete_collection |
Delete a collection and its videos |
list_videos |
List videos (filter by collection/status) |
get_video |
Get video details and URLs |
delete_video |
Delete a video |
get_upload_instructions |
Get upload commands |
list_webhooks |
List webhooks and available events |
get_webhook |
Get webhook details and deliveries |
create_webhook |
Create a webhook (returns secret once) |
update_webhook |
Update a webhook |
test_webhook |
Send test webhook event |
delete_webhook |
Delete a webhook |
get_embed_settings |
Get embed player settings |
update_embed_settings |
Update embed player settings |
sign_embed |
Generate signed embed URL/code |
list_api_keys |
List API keys |
create_api_key |
Create API key (returns key once) |
delete_api_key |
Delete API key |
get_account |
Get account settings |
update_account |
Update account settings |
get_usage |
Get usage stats and limits |
Resources
The server also provides documentation resources:
playvideo://docs/quickstart- Quick start guideplayvideo://docs/api- API referenceplayvideo://docs/sdks- SDK installation and examplesplayvideo://docs/webhooks- Webhook setup and verification
Environment Variables
| Variable | Required | Description |
|---|---|---|
PLAYVIDEO_API_KEY |
Yes | Your PlayVideo API key |
PLAYVIDEO_URL |
No | API URL (default: https://api.playvideo.dev) |
Self-Hosted PlayVideo
If you're running a self-hosted PlayVideo instance:
{
"mcpServers": {
"playvideo": {
"command": "playvideo-mcp",
"env": {
"PLAYVIDEO_API_KEY": "your-key",
"PLAYVIDEO_URL": "https://video.yourdomain.com"
}
}
}
}
Security
- API keys are never logged or exposed in responses
- All API calls go directly to PlayVideo servers
- No data is stored locally
License
MIT
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。