Supadata

Supadata MCP Server provides integration with Supadata to extract video transcripts, discover and crawl web pages, and retrieve rich media metadata through a single MCP endpoint. You can connect your AI assistant to access transcript extraction, web scraping, URL discovery, and AI-powered data extraction from video content directly in your workflows.

How to use

Connect an MCP client to the Supadata endpoint to enable transcript extraction, metadata retrieval, and AI-driven data extraction. You can request transcripts from supported platforms, fetch page metadata, map site URLs for discovery, crawl multi-page content, and run AI-based extraction on video content. Use the HTTP MCP URL and your API key to authorize requests, then call the corresponding MCP tools from your client.

How to install

Prepare your environment and obtain your API key from Supadata. Then configure your MCP client to connect to the Supadata MCP server over HTTP using the provided endpoint and API key header.

claude mcp add --transport http supadata https://api.supadata.ai/mcp \
  --header "x-api-key: YOUR_SUPADATA_API_KEY"

Configuration examples for clients

Below are representative configuration snippets you can adapt for your MCP-enabled clients. Replace YOUR_SUPADATA_API_KEY with your actual key.

{
  "mcpServers": {
    "supadata": {
      "url": "https://api.supadata.ai/mcp",
      "headers": {
        "x-api-key": "YOUR_SUPADATA_API_KEY"
      }
    }
  }
}

Environment variables

The following environment variable is used by the MCP configuration.

SUPADATA_API_KEY=YOUR_SUPADATA_API_KEY

Available tools

transcript

Extract transcripts from supported video platforms (YouTube, TikTok, Instagram, Twitter) and file URLs.

check_transcript_status

Check the progress of a transcript extraction job using the job ID.

metadata

Fetch metadata from a media URL on supported platforms. Returns platform info, title, description, author details, engagement stats, media details, tags, and creation date.

extract

Extract structured data from a video URL using AI. Provide a prompt or a JSON Schema for the output, or both; returns a job ID for async processing.

check_extract_status

Check the progress of an extraction job using the job ID.

scrape

Extract content from a single URL with advanced options.

map

Discover all indexed URLs on a website to identify relevant pages before scraping.

crawl

Start an asynchronous crawl job to extract content from multiple pages on a site.

check_crawl_status

Check the progress of a crawl job using the job ID.