MCP Server for Social Media Data

Set it up in your client

claude.ai

Settings → Connectors → Add custom connector, then paste the server URL:

https://mcp.scrapersocial.com

OAuth sign-in — no key to copy. Works on web, desktop, and mobile.

Claude Code

One command in your terminal:

claude mcp add --transport http \
  scrapersocial https://mcp.scrapersocial.com

Approve the OAuth prompt on first use, or set an Authorization header with your key.

Cursor

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "scrapersocial": {
      "url": "https://mcp.scrapersocial.com",
      "headers": { "Authorization": "Bearer sk_live_..." }
    }
  }
}

ChatGPT & others

Any client that supports remote MCP servers (streamable HTTP) works: add https://mcp.scrapersocial.com as a connector and authenticate with OAuth or a bearer key.

URL:  https://mcp.scrapersocial.com
Auth: OAuth 2.1 (PKCE) or
      Authorization: Bearer sk_live_...

Eight tools, five platforms

Tools take a URL or handle (plus a platform where it's ambiguous) and return the same clean JSON as the REST API.

get_transcript Transcript of a public video (TikTok, Instagram, Facebook, X)

get_summary Short AI summary of a video, built on its transcript

get_post_stats Views, likes, comments and shares for any public post

get_comments Paginated comments on a post

get_profile Profile or page stats for a handle or URL

get_channel_posts Latest posts or videos from an account

search_tiktok Keyword search over TikTok videos

search_instagram_reels Keyword search over Instagram reels

Recipes to steal

> transcribe the last 10 videos from @handle and summarize the themes

Chains get_channel_posts → get_transcript × 10, then the model summarizes.

> compare engagement on our last 5 posts vs @competitor's

Two get_channel_posts calls, one table — no glue code.

> what are people saying in the comments of this launch video?

get_comments with the URL, then sentiment and quotes from the model.

Your agent, connected to social data