官方Supadata MCP服务器——为Cursor、Claude及其他LLM客户端添加强大的视频和网页爬虫功能。
概览
一个模型上下文协议(MCP)服务器,与 Supadata 集成,用于视频文字记录提取、网页爬取、爬取和网站发现。 - 来自YouTube、TikTok、Instagram、Twitter及文件URL的访问 - 网页抓取、爬取和URL发现 - 从YouTube、TikTok、Instagram和Twitter获取媒体元数据 - 从视频内容中提取AI驱动的结构化数据 - 自动重试和速率限制 关于Claude、ChatGPT、Cursor、Windsurf、VS Code及其他客户端的设置说明,请参见集成指南。
概述(AI 翻译)
一个模型上下文协议(MCP)服务器,与 Supadata 集成,用于视频文字记录提取、网页爬取、爬取和网站发现。
特色
- 视频文字稿提取来自YouTube、TikTok、Instagram、Twitter及文件网址
- 网页爬取、爬取和URL发现
- 从YouTube、TikTok、Instagram和Twitter获取媒体元数据
- 从视频内容中提取AI驱动的结构化数据
安装
关于Claude、ChatGPT、Cursor、Windsurf、VS Code及其他客户端的设置说明,请参见集成指南。
跑步
Stdio(默认)
运行该包会启动 stdio 上的 MCP 服务器。这就是 MCP 客户端的配置 (Claude Desktop、光标、VS Code、Windsurf 等)在服务器生成时使用:
客户端配置示例:
可流式 HTTP(托管)
Cloudflare Worker 通过可流式 HTTP 提供相同的工具,在
src/worker.ts,部署于https://api.supadata.ai/mcp,随OAuth 2.1。
本地运行,使用 npm run dev(wrangler)。直接 x-api-key 头部
认证也支持/mcp。
OAuth 连接在使用期间保持有效,30天后失效 没有用处。
本页由 AI 翻译,技术细节请以原文为准。
README
以下为原文 README 节选,完整内容请查看原文。
Supadata MCP Server
A Model Context Protocol (MCP) server that integrates with Supadata for video transcript extraction, web scraping, crawling, and site discovery.
Features
- Video transcript extraction from YouTube, TikTok, Instagram, Twitter, and file URLs
- Web scraping, crawling, and URL discovery
- Media metadata retrieval from YouTube, TikTok, Instagram, and Twitter
- AI-powered structured data extraction from video content
Installation
For setup instructions for Claude, ChatGPT, Cursor, Windsurf, VS Code, and other clients, see the integration guide.
Running
Stdio (default)
Running the package starts an MCP server on stdio. This is what MCP clients (Claude Desktop, Cursor, VS Code, Windsurf, …) use when they spawn the server:
SUPADATA_API_KEY=your-api-key npx -y @supadata/mcp
Example client configuration:
{
"mcpServers": {
"supadata": {
"command": "npx",
"args": ["-y", "@supadata/mcp"],
"env": { "SUPADATA_API_KEY": "your-api-key" }
}
}
}
Streamable HTTP (hosted)
The same tools are served over Streamable HTTP by the Cloudflare Worker in
src/worker.ts, deployed at https://api.supadata.ai/mcp with OAuth 2.1.
Run it locally with npm run dev (wrangler). Direct x-api-key header
authentication is also accepted on /mcp.
An OAuth connection stays alive while it is used and expires after 30 days
without use. Then clients have to log in again; Codex keeps retrying the
expired login instead of asking, so run codex mcp login supadata if Supadata
tools stop working in Codex.
Configuration
Environment Variables
SUPADATA_API_KEY: Your Supadata API key (required for the stdio server). Get one at dash.supadata.aiDEBUG: set totruefor verbose loggingRUN_STDIO: set totrueto force the stdio server to start when the module is imported rather than executed directly
How to Choose a Tool
Select the right tool based on your needs:
- Transcript: Extract video transcripts from platforms and file URLs
- Scrape: Extract content from a single page when you know the exact URL
- Map: Discover all available URLs on a website
- Crawl: Extract content from multiple related pages comprehensively
- Metadata: Fetch metadata from media URLs (YouTube, TikTok, Instagram, Twitter)
- Extract: Extract structured data from video content using AI
| Tool | Best for | Returns |
|---|---|---|
| transcript | Video transcript extraction | text/markdown |
| metadata | Media metadata retrieval | JSON object |
| extract | AI-powered structured extraction | JSON object |
| scrape | Single page content | markdown/html |
| map | URL discovery on a site | URL[] |
安装
npx -y @supadata/mcp配置
{
"mcpServers": {
"supadata": {
"command": "npx",
"args": ["-y", "@supadata/mcp"],
"env": { "SUPADATA_API_KEY": "your-api-key" }
}
}
}