MCP server

Your agent, connected to social data

One URL — https://mcp.scrapersocial.com — puts all 226 endpoints across 32 platforms in reach of your agent. Sign in with OAuth or paste an API key, and it can transcribe videos, pull stats, read comments and search.

Get your free API key Agent docs

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_...

14 tools, 32 platforms

Tools take a URL, handle or query plus the platform, and return the same clean JSON as the REST API. The last two reach anything the others don't wrap: list_endpoints finds the endpoint, call_endpoint runs it.

get_transcript Spoken-word transcript of a public video, with timestamped segments where the source publishes them.

get_summary Short LLM summary of what a public video actually says, built on its transcript.

get_post_stats Engagement stats for one public post or video: views, likes, comments, shares and reposts where the platform publishes them.

get_comments Comments on a public post or video, newest first, paginated with limit and cursor.

get_comment_replies The reply thread hanging off a single public comment.

get_profile Profile, page or channel record for a public account: follower and subscriber counts, bio, and totals.

get_channel_posts Recent public posts or videos from one account, with per-item metrics.

search Keyword search over one platform's public content.

search_hashtag Public posts carrying a hashtag.

get_reviews Public reviews and ratings for a product, business, app or company page.

download_media Direct media URLs for a public post or video, served from the platform's own CDN.

get_trending What is currently trending or rising on a platform.

list_endpoints Browse the whole API surface — every endpoint, its input and its credit cost. Free, and calls nothing upstream.

call_endpoint Run any endpoint by its path, so nothing on the API is out of reach of an agent.

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.