Lets AI agents extract video transcripts, media metadata, and structured data from social media platforms and perform web scraping or crawling.
Also known as supadata-ai/mcp, mcp
- Stars
- 63
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 1.3.6
- Last commit
- Nov 4, 2026
- License
- MIT
What is Supadata MCP?
Supadata lets AI agents extract video transcripts, media metadata, and structured data from social media platforms and perform web scraping or crawling.
Summary generated from the project's README
About Supadata MCP server
Supadata provides a suite of tools for AI agents to interact with social media and web content. It enables developers to pull video transcripts from platforms like YouTube, TikTok, Instagram, and Twitter, or retrieve detailed media metadata. The server also supports web scraping, crawling multiple pages, and discovering URLs on a website through mapping tools.
Users can connect via a hosted HTTP server using OAuth 2.1 or run a local instance using stdio with a SUPADATA_API_KEY. It integrates with popular AI clients including Claude, ChatGPT, Cursor, and Claude Code. For more complex tasks, the extract tool uses AI to turn video content into structured JSON data based on specific prompts or schemas.
This server is designed for developers building agents that need to process social media data or perform deep web research. It includes asynchronous job management for long-running tasks like crawling or extraction, allowing agents to check status using specific job IDs.
What you can do with it
- 1Extract social media transcriptsAn AI agent can retrieve the text from a YouTube or TikTok video to summarize its contents.
- 2Perform structured video data extractionA developer can instruct an agent to pull specific information from a video into a JSON format using a prompt.
- 3Conduct comprehensive website crawlingAn agent can be tasked with gathering content from many different pages on a single website.
- 4Discover website URLsA user can ask an agent to find all available links on a specific domain before scraping them.
Written from the project's README. Every use case is checked against a quote from it.
How to install Supadata MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Supadata MCP in Claude Code
$ claude mcp add --transport http mcp https://api.supadata.ai/mcpInstall Supadata MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"mcp": {
"url": "https://api.supadata.ai/mcp"
}
}
}Install Supadata MCP in VS Code
.vscode/mcp.json
{
"servers": {
"mcp": {
"type": "http",
"url": "https://api.supadata.ai/mcp"
}
}
}Install Supadata MCP in VS Code CLI
$ code --add-mcp '{"name":"mcp","type":"http","url":"https://api.supadata.ai/mcp"}'Install Supadata MCP in Codex
$ codex mcp add mcp --url https://api.supadata.ai/mcpInstall Supadata MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.mcp] url = "https://api.supadata.ai/mcp"
Install Supadata MCP in Gemini CLI
$ gemini mcp add -s user --transport http mcp https://api.supadata.ai/mcpInstall Supadata MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"mcp": {
"url": "https://api.supadata.ai/mcp",
"type": "http"
}
}
}Configuration
SUPADATA_API_KEY
| Name | Description | |
|---|---|---|
| SUPADATA_API_KEY | — |
Automated checks
Ran Nov 12, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablePass
- Open source license (OSI)Pass
- Commit or release in the last yearPass
- Package name not close to a popular packageNot checked
- Remote endpoint uses HTTPSPass
- Destructive tools are labelledNot checked
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesNot checked
README
View on GitHubSupadata MCP Server
Use Supadata in your AI agent: video transcripts, media metadata, web scraping, crawling, and site discovery. This repository is the Supadata MCP server (Model Context Protocol), which AI agents like Claude, ChatGPT and Cursor use to call Supadata.
Add to your AI agent
Click a button, then sign in with your Supadata account. No API key to copy.
- Claude: click Add to Claude, click Connect and sign in. Works in claude.ai, Claude Desktop and the mobile apps. On Team/Enterprise plans an Owner enables Supadata first in Admin settings → Connectors.
- ChatGPT: click Add to ChatGPT, click Connect and sign in.
- Cursor: click Add to Cursor, confirm Install, and Cursor opens the Supadata sign-in page.
Claude Code / Codex
# Claude Code: then run /mcp and choose Authenticate
claude mcp add --transport http supadata https://api.supadata.ai/mcp
# Codex
codex mcp add supadata --url https://api.supadata.ai/mcp
codex mcp login supadata
Other MCP clients can connect to the hosted server at https://api.supadata.ai/mcp (OAuth, or an x-api-key header), or run the local server below.
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 step-by-step setup in Claude, ChatGPT, Cursor, Claude Code, Codex, Windsurf, VS Code and other AI agents, see the AI agents guide.
Running
Stdio (default)
Running the package starts an MCP server on stdio. Use this when your AI agent should spawn the server locally with your API key instead of using the hosted server (for example a custom agent, or VS Code / Windsurf config files):
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[] |
| crawl | Multi-page extraction | markdown/html[] |
Available Tools
Transcript (supadata_transcript)
Extract transcripts from supported video platforms (YouTube, TikTok, Instagram, Twitter) and file URLs.
Usage:
supadata_transcript --url "https://youtube.com/watch?v=example" --lang "en"
Check Transcript Status (supadata_check_transcript_status)
Check the progress of a transcript extraction job using the job ID.
Usage:
supadata_check_transcript_status --id "550e8400-e29b-41d4-a716-446655440000"
Metadata (supadata_metadata)
Fetch metadata from a media URL on supported platforms (YouTube, TikTok, Instagram, Twitter). Returns platform info, title, description, author details, engagement stats, media details, tags, and creation date.
Usage:
supadata_metadata --url "https://youtube.com/watch?v=example"
Extract (supadata_extract)
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 job ID for async processing.
Usage:
supadata_extract --url "https://youtube.com/watch?v=example" --prompt "Extract the main topics discussed"
Check Extract Status (supadata_check_extract_status)
Check the progress of an extract job using the job ID.
Usage:
supadata_check_extract_status --id "550e8400-e29b-41d4-a716-446655440000"
Scrape (supadata_scrape)
Extract content from a single URL with advanced options.
Usage:
supadata_scrape --url "https://example.com" --lang "en"
Map (supadata_map)
Discover all indexed URLs on a website to find relevant pages before scraping.
Usage:
supadata_map --url "https://example.com"
Crawl (supadata_crawl)
Start an asynchronous crawl job to extract content from multiple pages on a site.
Usage:
supadata_crawl --url "https://example.com/blog" --limit 100
Check Crawl Status (supadata_check_crawl_status)
Check the progress of a crawl job using the job ID.
Usage:
supadata_check_crawl_status --id "550e8400-e29b-41d4-a716-446655440000"
Development
# Install dependencies
npm install
# Build
npm run build
# Run tests
npm test
Contributing
- Fork the repository
- Create your feature branch
- Run tests:
npm test - Submit a pull request
License
MIT License - see LICENSE file for details
Supadata MCP questions
How do I add Supadata MCP to Claude Code?
Run claude mcp add --transport http mcp https://api.supadata.ai/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Supadata MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What kind of data can I extract from videos?
You can extract video transcripts, media metadata (like title, description, and engagement stats), and use AI to extract specific structured data based on a prompt.