# Supadata

Extract video transcripts and post metadata from major social platforms, scrape web pages, and map site URLs inside coding agents.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 63
- Author: supadata-ai
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/supadata-ai/mcp
- Updated: 2026-10-23
- HTML: https://affpapa.org/en/nevibecode/mcp/supadata

## What it does

The server provides tools for media processing and web discovery. It retrieves transcripts from YouTube, TikTok, Instagram, and Twitter media, along with author metrics and engagement figures. In addition, `supadata_extract` handles targeted extraction from video footage into custom JSON schemas via AI prompts.

For web exploration, tools include single-page fetching with `supadata_scrape` and domain indexing via `supadata_map`. To collect multiple related pages, `supadata_crawl` starts a background crawl. Long-running jobs execute asynchronously. Clients monitor completion status using generated job IDs.

Execution is possible via local stdio using `@supadata/mcp` or through the hosted Streamable HTTP endpoint at `https://api.supadata.ai/mcp`. Local stdio requires an active `SUPADATA_API_KEY` from `dash.supadata.ai`. Remote OAuth connections expire after 30 days of inactivity, and Codex will not refresh the expired session automatically without running `codex mcp login supadata`.

## Requirements
- Remote server: `https://api.supadata.ai/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http mcp https://api.supadata.ai/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add supadata --url https://api.supadata.ai/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "supadata": {
            "url": "https://api.supadata.ai/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "supadata": {
            "type": "http",
            "url": "https://api.supadata.ai/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http supadata https://api.supadata.ai/mcp
```

## When to use it
- retrieve full text transcripts from online video URLs
- collect publisher information and engagement counts from social posts
- extract structured data from video recordings using JSON schemas
- generate a site map of indexed URLs before scraping
- run asynchronous multi-page crawling across website directories

## Example prompts
- Summarize the discussion from this YouTube link: `https://youtube.com/watch?v=example`
- Map out all available URLs on `https://example.com`
- Extract author details and engagement stats from `https://youtube.com/watch?v=example`

## Similar
- [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 89433
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [AIHawk](https://affpapa.org/en/nevibecode/mcp/aihawk.md) — MCP server · ★ 32221
- [Skyvern](https://affpapa.org/en/nevibecode/mcp/skyvern.md) — MCP server · ★ 23263
- [SeleniumBase MCP](https://affpapa.org/en/nevibecode/mcp/seleniumbase-mcp.md) — MCP server · ★ 13169
- [apify-mcp-server](https://affpapa.org/en/nevibecode/mcp/apify-mcp-server.md) — MCP server · ★ 12927

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md