# Social Scrapers (remote · socialscrapers-gateway.socialscrapers.workers.dev)

Live public data from Instagram, YouTube and TikTok: profiles, posts, comments, transcripts, search.

- Trust score: 68/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `socialscrapers-gateway.socialscrapers.workers.dev`: 68/100 (this document), [markdown](https://verifymcp.io/servers/dev-workers-socialscrapers-socialscrapers-gateway-social-data/socialscrapers-gateway.md), [page](https://verifymcp.io/servers/dev-workers-socialscrapers-socialscrapers-gateway-social-data/socialscrapers-gateway)

## Channel facts

- Endpoint: `https://socialscrapers-gateway.socialscrapers.workers.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 67/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2889 tokens (~192/item across 15 items; 15 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 15 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Social Scrapers MCP server?

Social Scrapers is a hosted endpoint at https://socialscrapers-gateway.socialscrapers.workers.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http dev-workers-socialscrapers-socialscrapers-gatewa 'https://socialscrapers-gateway.socialscrapers.workers.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "dev-workers-socialscrapers-socialscrapers-gatewa": {
      "url": "https://socialscrapers-gateway.socialscrapers.workers.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "dev-workers-socialscrapers-socialscrapers-gatewa": {
      "type": "http",
      "url": "https://socialscrapers-gateway.socialscrapers.workers.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.dev-workers-socialscrapers-socialscrapers-gatewa]
url = "https://socialscrapers-gateway.socialscrapers.workers.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-workers-socialscrapers-socialscrapers-gatewa": {
      "type": "remote",
      "url": "https://socialscrapers-gateway.socialscrapers.workers.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dev-workers-socialscrapers-socialscrapers-gatewa --url 'https://socialscrapers-gateway.socialscrapers.workers.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  dev-workers-socialscrapers-socialscrapers-gatewa:
    url: "https://socialscrapers-gateway.socialscrapers.workers.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "dev-workers-socialscrapers-socialscrapers-gatewa": {
      "Transport": "http",
      "Url": "https://socialscrapers-gateway.socialscrapers.workers.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add dev-workers-socialscrapers-socialscrapers-gatewa -t streamable-http -u 'https://socialscrapers-gateway.socialscrapers.workers.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "dev-workers-socialscrapers-socialscrapers-gatewa": {
      "type": "http",
      "url": "https://socialscrapers-gateway.socialscrapers.workers.dev/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-20 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-18 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-16 (score 66, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-15 (score 65)

First indexed and scored.

## MCP tools (15)

### `instagram_profile` (~151 tokens)

Instagram profile

Get a public Instagram profile: exact follower, following and post counts, full name, bio and bio links, verified badge, account type (personal, business or creator), and its 12 latest posts (pinned first, as on the profile) with likes, comments, reel plays, captions and dates. For older posts, call instagram_posts with the next_cursor returned here.

Input parameters:

- `include_media_urls` (boolean): Also return picture, video and sound file links (long links that expire after a while). Leave it off unless you need the files.
- `username` (string, required): An Instagram username (natgeo), @natgeo, or a profile link (https://www.instagram.com/natgeo/).

### `instagram_posts` (~190 tokens)

Instagram posts of a profile

List a public Instagram profile's posts and reels, newest first (pinned posts first on the first page), 12 per page, each with likes, comments, reel plays, caption, hashtags, mentions, date, tagged accounts and collaborators. First page: give username. Next pages: give only cursor (the next_cursor of the previous answer) until next_cursor is null.

Input parameters:

- `cursor` (string): The next_cursor of the previous answer, exactly as returned, for the next page. Leave it out for the first page; with it, nothing else is needed.
- `include_media_urls` (boolean): Also return picture, video and sound file links (long links that expire after a while). Leave it off unless you need the files.
- `username` (string): An Instagram username (natgeo), @natgeo, or a profile link (https://www.instagram.com/natgeo/).

### `instagram_post` (~151 tokens)

Instagram post or reel

Get one public Instagram post or reel: caption, likes, comment count, date, carousel items, hashtags, mentions, tagged accounts, collaborators, location, paid-partnership flag and sponsors, and for a reel its play count, duration and sound. For its comments, call instagram_comments.

Input parameters:

- `include_media_urls` (boolean): Also return picture, video and sound file links (long links that expire after a while). Leave it off unless you need the files.
- `url` (string, required): A post or reel link (https://www.instagram.com/p/DfahZrMjAqq/ or /reel/…), its short code (DfahZrMjAqq) or its numeric id.

### `instagram_comments` (~198 tokens)

Instagram comments of a post

List the comments on a public Instagram post or reel, newest first, about two dozen per page: text, date, likes, reply count and the commenter's username and verified badge. The first page also gives the post's comment count. First page: give url. Next pages: give only cursor until next_cursor is null.

Input parameters:

- `cursor` (string): The next_cursor of the previous answer, exactly as returned, for the next page. Leave it out for the first page; with it, nothing else is needed.
- `include_media_urls` (boolean): Also return picture, video and sound file links (long links that expire after a while). Leave it off unless you need the files.
- `url` (string): A post or reel link (https://www.instagram.com/p/DfahZrMjAqq/ or /reel/…), its short code (DfahZrMjAqq) or its numeric id.

### `instagram_hashtag` (~194 tokens)

Instagram top posts for a hashtag or keyword

Get the top posts Instagram shows for a hashtag or keyword, in Instagram's order, up to 50 per page, each with caption, hashtags, likes, comments, reel plays, date and the creator; the first page also lists related searches. Instagram shows 50 to 100 top posts per search in all. First page: give tag. Next pages: give only cursor until next_cursor is null.

Input parameters:

- `cursor` (string): The next_cursor of the previous answer, exactly as returned, for the next page. Leave it out for the first page; with it, nothing else is needed.
- `include_media_urls` (boolean): Also return picture, video and sound file links (long links that expire after a while). Leave it off unless you need the files.
- `tag` (string): A hashtag (sourdough or #sourdough), a keyword (running shoes) or a hashtag link.

### `youtube_video` (~134 tokens)

YouTube video details

Get a public YouTube video, Short or live stream: title, description, exact publish time, length, views, likes, exact comment count, tags and hashtags, category, chapters, links in the description, thumbnail, live status, members-only and age-restricted flags, and its channel with subscriber count and verified badge. For what is said in it, call youtube_transcript; for its comments, youtube_comments.

Input parameters:

- `url` (string, required): A YouTube video link (watch, youtu.be, Shorts, live or embed link) or its 11-character id (_T8cn2J13-4).

### `youtube_transcript` (~253 tokens)

YouTube video transcript

Get what is said in a YouTube video: its transcript in any language the video has captions in (human-made captions before auto-generated ones), with its title, channel, length, the language returned and every available language. format=text (default) gives the plain text; format=segments gives timed lines with start and duration in seconds. A very long transcript is cut at a line to keep the answer small, and the answer then names the start_seconds to call again with to read on. Videos without captions have no transcript.

Input parameters:

- `format` (string): text: the plain transcript. segments: timed lines (start and duration in seconds).
- `lang` (string): A language code (en, es, pt-BR, zh-Hans). Leave it out for the default captions, usually the spoken language. Without captions in that language, the default ones are returned.
- `start_seconds` (integer): Read from this point of the video, in seconds. Used to continue a transcript that was cut.
- `url` (string, required): A YouTube video link (watch, youtu.be, Shorts, live or embed link) or its 11-character id (_T8cn2J13-4).

### `youtube_search` (~246 tokens)

YouTube search

Search YouTube: one page of results in YouTube's order (about 20 videos, plus the Shorts and channels YouTube shows with them), each with title, views, length, age, channel and description snippet. Filter by result type, upload date, duration, sort order and features. First page: give query (and any filters). Next pages: give only cursor until next_cursor is null.

Input parameters:

- `cursor` (string): The next_cursor of the previous answer, exactly as returned, for the next page. Leave it out for the first page; with it, nothing else is needed.
- `duration` (string): Only videos of one length: short (under 4 minutes), medium (4 to 20 minutes), long (over 20 minutes).
- `features` (array): Features every video must have.
- `query` (string): The search terms, or a YouTube search link (its filters are kept).
- `sort` (string): Order of the results.
- `type` (string): Only results of one type.
- `upload_date` (string): Only videos uploaded in the last hour, today, this week, this month or this year.

### `youtube_channel` (~125 tokens)

YouTube channel details

Get a public YouTube channel: name, handle, description, subscriber count, video count, total views, join date, country, the links on its About page, keywords, avatar, banner and verified badge. For its uploads, call youtube_channel_videos.

Input parameters:

- `channel` (string, required): A YouTube channel: an @handle (@NASA), a channel link (https://www.youtube.com/@NASA, /channel/UC…, /c/…, /user/…) or a channel id (UCLA_DiR1FfKNvjuUpBHmylQ).

### `youtube_channel_videos` (~224 tokens)

YouTube channel's videos, Shorts or live streams

List a YouTube channel's uploads from its Videos, Shorts or Live tab, newest first, most popular first or oldest first, about 30 per page, each with title, views, length, age and thumbnail. A channel without that tab returns an empty page. First page: give channel (and tab, sort). Next pages: give only cursor until next_cursor is null.

Input parameters:

- `channel` (string): A YouTube channel: an @handle (@NASA), a channel link (https://www.youtube.com/@NASA, /channel/UC…, /c/…, /user/…) or a channel id (UCLA_DiR1FfKNvjuUpBHmylQ).
- `cursor` (string): The next_cursor of the previous answer, exactly as returned, for the next page. Leave it out for the first page; with it, nothing else is needed.
- `sort` (string): Newest first, most popular first, or oldest first.
- `tab` (string): The channel's Videos, Shorts or Live tab.

### `youtube_comments` (~184 tokens)

YouTube comments of a video

List a YouTube video's comments, top comments first or newest first, about 20 per page, each with author, text, likes, reply count, age, and pinned and creator-heart flags; the first page also gives the exact comment count. A video with comments turned off returns an empty page. First page: give url (and sort). Next pages: give only cursor until next_cursor is null.

Input parameters:

- `cursor` (string): The next_cursor of the previous answer, exactly as returned, for the next page. Leave it out for the first page; with it, nothing else is needed.
- `sort` (string): Top comments first, or newest first.
- `url` (string): A YouTube video link (watch, youtu.be, Shorts, live or embed link) or its 11-character id (_T8cn2J13-4).

### `tiktok_profile` (~158 tokens)

TikTok profile

Get a public TikTok profile: exact follower, following, like and video counts, nickname, bio and bio link, verified badge, region and language, business and organization flags, and its newest videos (up to 15) with plays, likes, comments and captions. A private account's profile is returned without videos. For older videos, call tiktok_videos with the next_cursor returned here.

Input parameters:

- `include_media_urls` (boolean): Also return picture, video and sound file links (long links that expire after a while). Leave it off unless you need the files.
- `username` (string, required): A TikTok username (nasa), @nasa, or a profile link (https://www.tiktok.com/@nasa).

### `tiktok_videos` (~181 tokens)

TikTok videos of a profile

List a public TikTok profile's videos and photo posts, newest first, up to 15 per page, each with plays, likes, comments, shares, saves, caption, hashtags, mentions, date, duration and sound. First page: give username. Next pages: give only cursor until next_cursor is null.

Input parameters:

- `cursor` (string): The next_cursor of the previous answer, exactly as returned, for the next page. Leave it out for the first page; with it, nothing else is needed.
- `include_media_urls` (boolean): Also return picture, video and sound file links (long links that expire after a while). Leave it off unless you need the files.
- `username` (string): A TikTok username (nasa), @nasa, or a profile link (https://www.tiktok.com/@nasa).

### `tiktok_video` (~163 tokens)

TikTok video or photo post

Get one public TikTok video or photo post: caption, plays, likes, comments, shares, saves, date, duration, hashtags, mentions, sound, location, categories, the ad flag, and its author with their counts. For its comments, call tiktok_comments.

Input parameters:

- `include_media_urls` (boolean): Also return picture, video and sound file links (long links that expire after a while). Leave it off unless you need the files.
- `url` (string, required): A TikTok video or photo link (https://www.tiktok.com/@nasa/video/7695060950394703118), a short link from the app (vm.tiktok.com/…, vt.tiktok.com/…, tiktok.com/t/…) or the video id.

### `tiktok_comments` (~249 tokens)

TikTok comments of a video, or replies to a comment

List a TikTok video's comments in TikTok's order, up to 50 per page: text, date, likes, reply count, whether the creator liked or pinned it, language and the commenter. With comment_id, list the replies to that comment instead. First page: give url (and comment_id for replies). Next pages: give only cursor until next_cursor is null.

Input parameters:

- `comment_id` (string): The id of one of the video's comments (from a previous answer), to list its replies.
- `cursor` (string): The next_cursor of the previous answer, exactly as returned, for the next page. Leave it out for the first page; with it, nothing else is needed.
- `include_media_urls` (boolean): Also return picture, video and sound file links (long links that expire after a while). Leave it off unless you need the files.
- `url` (string): A TikTok video or photo link (https://www.tiktok.com/@nasa/video/7695060950394703118), a short link from the app (vm.tiktok.com/…, vt.tiktok.com/…, tiktok.com/t/…) or the video id.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/dev-workers-socialscrapers-socialscrapers-gateway-social-data/socialscrapers-gateway#diagnostics

## Score history

- 2026-11-21: 68
- 2026-11-20: 68
- 2026-11-19: 67
- 2026-11-18: 67
- 2026-11-17: 66
- 2026-11-16: 66
- 2026-11-15: 65

## Common questions

### What is the Social Scrapers MCP server?

Social Scrapers is an MCP server listed in the public MCP registry as dev.workers.socialscrapers.socialscrapers-gateway/social-da…. Live public data from Instagram, YouTube and TikTok: profiles, posts, comments, transcripts, search. This page covers its hosted endpoint (https://socialscrapers-gateway.socialscrapers.workers.dev/mcp).

### Is the Social Scrapers MCP server safe to use?

Social Scrapers scores 68 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Social Scrapers MCP server expose?

Social Scrapers exposes 15 tools: instagram_profile, instagram_posts, instagram_post, instagram_comments, instagram_hashtag, and 10 more. Their descriptions and schemas cost roughly 2,801 tokens of context every time the server is loaded.

### Does the Social Scrapers MCP server require authentication?

No. We connected to Social Scrapers without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Social Scrapers MCP server still maintained?

Social Scrapers is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Social Scrapers MCP server?

VerifyMCP ran 12 checks on Social Scrapers, covering TLS certificate, Authorization, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about Social Scrapers: HTTPS. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://socialscrapers-gateway.socialscrapers.workers.dev/mcp
- Authorisation metadata: https://socialscrapers-gateway.socialscrapers.workers.dev/.well-known/oauth-protected-resource/mcp
- Website: https://socialscrapers-site.socialscrapers.workers.dev/
- Changelog RSS feed: https://verifymcp.io/servers/dev-workers-socialscrapers-socialscrapers-gateway-social-data/socialscrapers-gateway.xml
- Changelog JSON feed: https://verifymcp.io/servers/dev-workers-socialscrapers-socialscrapers-gateway-social-data/socialscrapers-gateway/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/dev-workers-socialscrapers-socialscrapers-gateway-social-data/socialscrapers-gateway.json
- HTML version of this page: https://verifymcp.io/servers/dev-workers-socialscrapers-socialscrapers-gateway-social-data/socialscrapers-gateway
