Supadata MCP Server

Video transcript extraction and web scraping via Supadata for AI assistants.

Data last scanned last week · Reviewed last month

389 tools★ 61TypeScriptMIT

Overview

The Supadata MCP Server bridges the Supadata platform with your AI client, enabling advanced content retrieval capabilities. It supports video transcript extraction from major social platforms like YouTube, TikTok, Instagram, and Twitter, alongside file URL processing. Beyond media, the server facilitates comprehensive web data workflows including single-page scraping, site-wide URL mapping, and multi-page crawling. Users can also utilize AI-powered structured data extraction to parse video content into structured JSON formats.

Our verdict

This server carries a high-risk rating with a security score of 38/100. It is a community-maintained project rather than an official vendor release, and critical aspects such as OAuth implementation, authentication methods, and read-only mode support remain unreviewed. Due to these unresolved security concerns and the lack of independent editorial validation, it is recommended only for development or testing environments where sensitive data exposure can be strictly mitigated.

Supports extraction from YouTube, TikTok, Instagram, and Twitter.
Provides automated retry and rate limiting configuration parameters.
Includes structured data extraction for video content.
Limited dependency count with only 7 direct dependencies.

Community-maintained with no official vendor oversight.
Security score of 38/100 indicating significant audit gaps.
Authentication and OAuth support remain unreviewed.
Read-only mode implementation has not yet been audited.

Setup

Claude Desktop

{
  "mcpServers": {
    "supadata-ai-mcp": {
      "args": [
        "-y",
        "@supadata/mcp"
      ],
      "command": "npx"
    }
  }
}

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows), then restart Claude Desktop. Some servers require API keys or tokens as environment variables — check the project's README and add an "env" object if needed.

No read-only mode — running this grants full read/write access.
No built-in authentication — anyone with access to this config can invoke every tool it exposes.

Tools

Tool	Description	Risk
supadata_transcript	Extract transcripts from supported video platforms and file URLs.	low
supadata_check_transcript_status	Check the progress of a transcript extraction job using the job ID.	low
supadata_metadata	Fetch metadata from a media URL on supported platforms.	low
supadata_extract	Extract structured data from a video URL using AI.	medium
supadata_check_extract_status	Check the progress of an extract job using the job ID.	low
supadata_scrape	Extract content from a single URL with advanced options.	low
supadata_map	Discover all indexed URLs on a website to find relevant pages before scraping.	low
supadata_crawl	Start an asynchronous crawl job to extract content from multiple pages on a site.	medium
supadata_check_crawl_status	Check the progress of a crawl job using the job ID.	low

Compatibility

Client	Local	Docker	Remote	Read-only
ChatGPT
Claude Desktop
Cursor
VS Code
Windsurf

Frequently asked questions

›What is required to configure the Supadata MCP server?

You must provide a valid Supadata API key through the SUPADATA_API_KEY environment variable.

›Can I check the progress of long-running operations?

Yes, the server provides dedicated check status tools for transcript, extract, and crawl jobs that return a job ID.

›Does the server support automated retries for failed requests?

Yes, the server includes configurable retry parameters including max attempts, initial delay, and exponential backoff.

›Which platforms are supported for video transcript and metadata extraction?

Supported platforms include YouTube, TikTok, Instagram, and Twitter.

›How can I extract specific information from a video using AI?

You can use the supadata_extract tool, which allows you to provide a custom prompt and JSON schema to control the AI-powered structured data extraction.