Documentation Index
Fetch the complete documentation index at: https://docs.supadata.ai/llms.txt
Use this file to discover all available pages before exploring further.
Overview
The Supadata MCP (Model Context Protocol) server enables powerful web and video scraping capabilities directly within AI development environments like Cursor, Claude Desktop, and VS Code. This open-source integration allows AI models to extract transcripts, scrape web pages, and crawl entire websites to gather context.Features
- Multi-Platform Support: Works with YouTube, TikTok, Instagram, Twitter, and more
- AI-First Design: Optimized for use with LLMs and AI assistants
- Multiple Tools: Transcript extraction, web scraping, site mapping, and crawling
- Easy Integration: Simple setup with popular AI tools
Installation
Manual Installation
Integration Setup
Claude / Claude Desktop / Cowork
Connect directly from Claude without manually configuring an API key.- Go to Settings → Connectors
- Click Add custom connector and enter
Supadataas the name andhttps://api.supadata.ai/mcpas the URL. Click Add.

- Click Authorize when prompted to grant MCP access.

Claude Code
- Add the Supadata MCP server:
- Run
/mcpin Claude Code and select Authenticate for Supadata to complete the OAuth flow in your browser.
ChatGPT
- Go to Settings → Apps & Connectors
- Click Create to add a new connector
- Enter
Supadataas the name andhttps://api.supadata.ai/mcpas the connector URL - Click Save
Cursor
- Open Cursor Settings
- Navigate to MCPs & Integrations → New MCP Server
- Add new MCP server:
Windsurf
Add to~/.windsurf/cascade/config.json:
VS Code
Using the MCP extension:- Install the MCP extension
- Add Supadata server configuration
- Set your API key in environment settings
Configuration
Environment Variables
X_API_KEY: Your Supadata API key (required)