Supadata 远程 MCP 服务器是什么?
Supadata 的远程 MCP 服务器是一个托管的 Model Context Protocol 端点,地址是 https://api.supadata.ai/mcp,AI 助手无需在本地安装或运行任何东西即可连接。
Supadata MCP Server
@supadata-ai
基本信息
关于 Supadata MCP Server
Turn YouTube, TikTok, X videos and websites into structured data.
连接信息
https://api.supadata.ai/mcp接入方式
claude mcp add supadata --transport http https://api.supadata.ai/mcpSupadata MCP Server 工具
9Get the transcript (what is said) of a video or post on YouTube, TikTok, Instagram, X (Twitter) or Facebook, or of an audio or video file URL. Not for ordinary web pages: use supadata_scrape for those. For large files, returns a jobId instead of the transcript directly - use supadata_check_transcript_status with that jobId to poll for results.
Check transcript job status and retrieve results. Returns status: "queued", "active", "completed", or "failed". If status is not "completed" or "failed", call this tool again after a few seconds with the same id.
Fetch a single web page and return its main content as Markdown, along with the page title, description and the links it contains. Use this to read or summarize a specific URL. To find which pages exist on a site, use supadata_map; to fetch many pages at once, use supadata_crawl. Costs 1 credit.
List the URLs found on a website without fetching their content. Use this to discover a site's pages before choosing which ones to read with supadata_scrape, or to check a site's size before starting a supadata_crawl. Costs 1 credit.
Create a crawl job to extract content from all pages on a website. Not available on every Supadata plan; if it returns upgrade-required, tell the user rather than retrying. Returns a jobId - use supadata_check_crawl_status with that jobId to poll for results.
Check crawl job status and retrieve results. Returns status: "scraping", "completed", "failed", or "cancelled". If status is "scraping", call this tool again after a few seconds with the same id.
Fetch metadata from a media URL (YouTube, TikTok, Instagram, Twitter/X, Facebook). Returns platform info, title, description, author details, engagement stats, media details, tags, and creation date. Use this for details about a video or post; use supadata_transcript for what is said in it.
Extract structured data from a video URL using AI. Provide a prompt for what to extract, a JSON Schema for the output format, or both. Returns a jobId for async processing - use supadata_check_extract_status with that jobId to poll for results.
Check extract job status and retrieve results. Returns status: "queued", "active", "completed", or "failed". If status is not "completed" or "failed", call this tool again after a few seconds with the same id.
概览
Supadata gives your AI agent access to what is said in online video and to the content of any public web page.
Paste a link to a video on YouTube, TikTok, Instagram, X or Facebook and your AI agent can fetch its transcript, with timestamps and in the caption languages available. When a video has no captions, Supadata can generate a transcript with AI. Your AI agent can also fetch a post's metadata (title, description, author, views, likes, comments, tags and publish date) and extract structured data from a video using a prompt or a JSON Schema.
For the web, your AI agent can read a single page as clean Markdown, list the URLs on a site, or crawl a whole site and read every page.
What you can do with it:
- Summarise, quote or fact-check a video without watching it
- Turn talks, podcasts and tutorials into notes, articles or study guides
- Compare engagement across videos and posts
- Pull structured data out of video, such as products, recipes or steps
- Bring documentation sites and articles into a conversation
Supadata only reads publicly available content. It does not post, edit or delete anything on any platform.
You need a Supadata account. Sign in when you connect; there is no API key to copy. The free plan includes 100 credits a month with no credit card. A transcript, a metadata lookup or a web page costs 1 credit. AI-generated transcripts and video extraction cost more, and website crawling requires the Pro plan or higher.
常见问题
怎么连接 Supadata 的 MCP 服务器?
把端点 https://api.supadata.ai/mcp 添加到任意支持 MCP 的客户端,比如 Claude Code、Cursor 或 VS Code。本页的接入代码块可以一步配置好每个客户端。
Supadata 的 MCP 服务器需要认证吗?
需要。Supadata 使用 OAuth——第一次连接时,你的 MCP 客户端会打开浏览器窗口登录并授权,之后会复用这个凭证。
Supadata 的 MCP 服务器用的是哪种传输方式?
Supadata 暴露的是 stdio 端点,这是远程 MCP 服务器普遍使用、主流客户端都支持的传输方式。
更多远程 MCP 服务器
9apes
The 9apes MCP server lets an AI assistant read the GitHub Actions data 9apes already collects for your organization: runs, jobs, steps, and their durations. Ask it why a build got slower, which jobs take the longest, or
ARVX
Email for long-term client relationships: ARVX reads each person first and remembers every pair.
A
ASO Atlas
App Store keyword research, rank tracking, competitor analysis and authorized performance data.
A
AccountHub
One MCP connection for all your Gmail, Google Calendar, Drive and Contacts accounts, Slack workspaces and Notion — free.
%20-%20Sarah%20Xu.svg){kind=icon}
Adobe Journey Optimizer
Understand and troubleshoot your Journeys and Campaigns
评论