# YouTube Scraper (remote · mcp.rapidapi.com)

YouTube videos, Shorts, comments, channels, contacts and transcripts as structured JSON.

- Trust score: 54/100 (low)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `mcp.rapidapi.com`: 54/100 (this document), [markdown](https://verifymcp.io/servers/coregentdevspace-youtube-scraper/mcp.md), [page](https://verifymcp.io/servers/coregentdevspace-youtube-scraper/mcp)

## Channel facts

- Endpoint: `https://mcp.rapidapi.com`
- 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**: 49/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 12 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS check failed: the endpoint is reachable over plaintext HTTP.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 43/100
  - AI-judged instruction clarity (fair).
  - Context-footprint check failed: tool/resource definitions use about 2087 tokens (~173/item across 12 items; 12 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 76/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 29% 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 12 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

## Install

### How do I install the YouTube Scraper MCP server?

YouTube Scraper is a hosted endpoint at https://mcp.rapidapi.com/, 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 coregentdevspace-youtube-scraper 'https://mcp.rapidapi.com/'
```

### Cursor

```json
{
  "mcpServers": {
    "coregentdevspace-youtube-scraper": {
      "url": "https://mcp.rapidapi.com/"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "coregentdevspace-youtube-scraper": {
      "type": "http",
      "url": "https://mcp.rapidapi.com/"
    }
  }
}
```

### Codex

```toml
[mcp_servers.coregentdevspace-youtube-scraper]
url = "https://mcp.rapidapi.com/"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "coregentdevspace-youtube-scraper": {
      "type": "remote",
      "url": "https://mcp.rapidapi.com/",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add coregentdevspace-youtube-scraper --url 'https://mcp.rapidapi.com/' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  coregentdevspace-youtube-scraper:
    url: "https://mcp.rapidapi.com/"
```

### Netclaw

```json
{
  "McpServers": {
    "coregentdevspace-youtube-scraper": {
      "Transport": "http",
      "Url": "https://mcp.rapidapi.com/"
    }
  }
}
```

### Vellum

```bash
assistant mcp add coregentdevspace-youtube-scraper -t streamable-http -u 'https://mcp.rapidapi.com/'
```

### Other

```json
{
  "mcpServers": {
    "coregentdevspace-youtube-scraper": {
      "type": "http",
      "url": "https://mcp.rapidapi.com/"
    }
  }
}
```

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.

### 2026-11-21 (score 54, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-18 (score 53, +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.

### 2026-11-16 (score 52, +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.

### 2026-11-14 (score 51, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-13 (score 50)

First indexed and scored.

## MCP tools (12)

### `YouTube_Channel_Contacts_Scraper` (~250 tokens)

Discover YouTube channels and extract contact info + social links from About pages. Returns 32 enriched fields (15 standard channel fields + 17 contact fields) as dataset items (sync).

Limits: Results per request are capped by plan (10/50/100/200).

Input parameters:

- `_endpoint` (string): Endpoint: POST /youtube/channel-contacts
- `_method` (string): HTTP method
- `callbackSecret`
- `callbackUrl`
- `dateFrom` (string)
- `dateTo` (string)
- `emailRegexMode` (string)
- `externalLinkDepth` (string)
- `includeContacts` (boolean)
- `includeEmailExtraction` (boolean)
- `includeExternalLinks` (boolean)
- `language` (string)
- `limit` (number)
- `maxConcurrency` (integer)
- `maxResultsPerQuery` (integer)
- `mode`
- `offset` (number)
- `regionCode` (string)
- `searchQueries` (array)
- `startUrls` (array): Channel/video/shorts/playlist/search URLs. Supports requestListSources objects.

### `Health_Check` (~46 tokens)

Returns API status. Use this to verify the wrapper base URL is reachable.

Input parameters:

- `_endpoint` (string): Endpoint: GET /health
- `_method` (string): HTTP method

### `YouTube_Shorts_Scraper` (~293 tokens)

Extract YouTube Shorts metadata (and optional transcripts) using keyword search, channels, hashtags, or direct Shorts URLs. Returns dataset items as JSON (sync).

Limits: Results per request are capped by plan (10/50/100/200).

Input parameters:

- `_endpoint` (string): Endpoint: POST /youtube/shorts
- `_method` (string): HTTP method
- `callbackSecret`
- `callbackUrl`
- `channelUrls` (array): Channel handles or URLs (e.g., "@mrbeast" or https://www.youtube.com/@mrbeast).
- `fromDate` (string): YYYY-MM-DD (optional).
- `hashtagSearch` (array): Hashtags to search (e.g., "#viral").
- `includeTranscript` (boolean)
- `keywordSearch` (array): Keywords to search (e.g., "cooking tips").
- `language` (string)
- `limit` (number)
- `maxResultsPerChannel` (integer)
- `maxResultsPerSearch` (integer)
- `mode`
- `offset` (number)
- `regionCode` (string)
- `shortsUrls` (array): Direct Shorts URLs.
- `sortShorts` (string)
- `toDate` (string): YYYY-MM-DD (optional).
- `transcriptLanguage` (string): Transcript language (used only when includeTranscript=true).

### `YouTube_Videos_Fast_Scraper` (~195 tokens)

High-performance YouTube video scraper. Supports keyword/channel searches and direct URL scraping. Returns dataset items as JSON (sync). Built on a hybrid approach (search discovery + YouTube Data API v3).

Limits: Results per request are capped by plan (10/50/100/200).

Input parameters:

- `_endpoint` (string): Endpoint: POST /youtube/videos-fast
- `_method` (string): HTTP method
- `callbackSecret`
- `callbackUrl`
- `dateFrom` (string)
- `dateTo` (string)
- `includeShorts` (boolean)
- `language` (string)
- `limit` (number)
- `maxResultsPerQuery` (integer)
- `mode`
- `offset` (number)
- `regionCode` (string)
- `searchQueries` (array)
- `startUrls` (array)

### `YouTube_Highlights__Hooks_Analyser` (~252 tokens)

Analyze YouTube videos to extract chapters, hook suggestions, and intro pacing metrics. Supports video URLs, channel URLs, and search queries. Returns rich analysis dataset items as JSON (sync).

Limits: Results per request are capped by plan (10/50/100/200).

Input parameters:

- `_endpoint` (string): Endpoint: POST /youtube/highlights
- `_method` (string): HTTP method
- `callbackSecret`
- `callbackUrl`
- `computeIntroPacing` (boolean)
- `dryRun` (boolean)
- `durationFilter` (string)
- `fetchTranscript` (boolean)
- `hookLengthSec` (integer)
- `limit` (number)
- `maxHooksPerVideo` (integer)
- `maxVideos` (integer)
- `maxViews` (integer)
- `minViews` (integer)
- `mode`
- `offset` (number)
- `searchQuery` (string)
- `since` (string): YYYY-MM-DD (optional)
- `sortBy` (string)
- `startUrls` (array)
- `until` (string): YYYY-MM-DD (optional)

### `YouTube_Transcript_Scraper` (~147 tokens)

Lightning-fast transcript extraction for YouTube videos (URLs, youtu.be links, or video IDs). Returns full transcript text, timed segments, and metadata as dataset items (sync).

Limits: Results per request are capped by plan (10/50/100/200).

Input parameters:

- `_endpoint` (string): Endpoint: POST /youtube/transcripts
- `_method` (string): HTTP method
- `callbackSecret`
- `callbackUrl`
- `limit` (number)
- `mode`
- `offset` (number)
- `videoRefs` (array, required): Full watch URLs, youtu.be URLs, or raw 11-char video IDs.

### `YouTube_Video_Finder` (~188 tokens)

Fast YouTube video discovery using a hybrid approach (Puppeteer for discovery + YouTube Data API v3 fallback). Returns 14 essential fields as dataset items (sync).

Limits: Results per request are capped by plan (10/50/100/200).

Input parameters:

- `_endpoint` (string): Endpoint: POST /youtube/video-finder
- `_method` (string): HTTP method
- `callbackSecret`
- `callbackUrl`
- `dateFrom` (string)
- `dateTo` (string)
- `includeShorts` (boolean)
- `language` (string)
- `limit` (number)
- `maxResultsPerQuery` (integer)
- `mode`
- `offset` (number)
- `regionCode` (string)
- `searchQueries` (array)
- `startUrls` (array)

### `YouTube_Channel_Finder` (~177 tokens)

Discover YouTube channels from search keywords and/or direct YouTube URLs (video/shorts/channel/playlist/search). Returns channel dataset items with 15 fields (sync).

Limits: Results per request are capped by plan (10/50/100/200).

Input parameters:

- `_endpoint` (string): Endpoint: POST /youtube/channel-finder
- `_method` (string): HTTP method
- `callbackSecret`
- `callbackUrl`
- `dateFrom` (string)
- `dateTo` (string)
- `language` (string)
- `limit` (number)
- `maxResultsPerQuery` (integer)
- `mode`
- `offset` (number)
- `regionCode` (string)
- `searchQueries` (array)
- `startUrls` (array)

### `Job_results` (~65 tokens)

Get paginated results for a completed job

Input parameters:

- `_endpoint` (string): Endpoint: GET /jobs/{jobId}/results
- `_method` (string): HTTP method
- `jobId` (required)
- `limit` (number)
- `offset` (number)

### `Job_status` (~45 tokens)

Get async job status

Input parameters:

- `_endpoint` (string): Endpoint: GET /jobs/{jobId}
- `_method` (string): HTTP method
- `jobId` (required)

### `YouTube_Videos_Scraper` (~254 tokens)

Scrape YouTube videos (and optionally Shorts) by keyword search, channel handles/IDs, playlists, or direct URLs. Returns full metadata as dataset items (JSON).

Limits: Results per request are capped by plan (10/50/100/200).

Input parameters:

- `_endpoint` (string): Endpoint: POST /youtube/videos
- `_method` (string): HTTP method
- `callbackSecret`
- `callbackUrl`
- `dateFrom` (string): YYYY-MM-DD. Applies to searchQueries only.
- `dateTo` (string): YYYY-MM-DD. Applies to searchQueries only.
- `includeShorts` (boolean): Include Shorts results in addition to videos.
- `language` (string)
- `limit` (number)
- `maxResultsPerQuery` (integer): Max results per search query.
- `mode`
- `offset` (number)
- `regionCode` (string)
- `searchQueries` (array): Search queries: keywords, @handle, channel ID, or playlist ID.
- `startUrls` (array): Direct URLs or remote URL list. Each item can be {"url": "..."} or {"requestsFromUrl": "..."}.

### `YouTube_Comments_Scraper` (~175 tokens)

Scrape YouTube comments (and optional replies) from one or more video URLs. Returns structured dataset items including comment text, author info, engagement metrics, and video metadata (sync).

Limits: Results per request are capped by plan (10/50/100/200).

Input parameters:

- `_endpoint` (string): Endpoint: POST /youtube/comments
- `_method` (string): HTTP method
- `callbackSecret`
- `callbackUrl`
- `includeReplies` (boolean)
- `limit` (number)
- `maxComments` (integer)
- `maxTimePerVideo` (integer): Seconds per video. If reached, returns partial results.
- `mode`
- `offset` (number)
- `startUrls` (array): YouTube video URLs (max 100).

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/coregentdevspace-youtube-scraper/mcp#diagnostics

## Score history

- 2026-11-21: 54
- 2026-11-20: 53
- 2026-11-19: 53
- 2026-11-18: 53
- 2026-11-17: 52
- 2026-11-16: 52
- 2026-11-15: 51
- 2026-11-14: 51
- 2026-11-13: 50

## Common questions

### What is the YouTube Scraper MCP server?

YouTube Scraper is an MCP server listed in the public MCP registry as io.github.coregentdevspace/youtube-scraper. YouTube videos, Shorts, comments, channels, contacts and transcripts as structured JSON. This page covers its hosted endpoint (https://mcp.rapidapi.com).

### Is the YouTube Scraper MCP server safe to use?

YouTube Scraper scores 54 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 YouTube Scraper MCP server expose?

YouTube Scraper exposes 12 tools: YouTube_Channel_Contacts_Scraper, Health_Check, YouTube_Shorts_Scraper, YouTube_Videos_Fast_Scraper, YouTube_Highlights__Hooks_Analyser, and 7 more. Their descriptions and schemas cost roughly 2,087 tokens of context every time the server is loaded.

### Does the YouTube Scraper MCP server require authentication?

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

### Is the YouTube Scraper MCP server still maintained?

YouTube Scraper 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 YouTube Scraper MCP server?

VerifyMCP ran 12 checks on YouTube Scraper, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about YouTube Scraper: Authorization. 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://mcp.rapidapi.com/
- Authorisation metadata: https://mcp.rapidapi.com/.well-known/oauth-protected-resource
- Website: https://rapidapi.com/coregentdevspace/api/youtube-scraper14
- Changelog RSS feed: https://verifymcp.io/servers/coregentdevspace-youtube-scraper/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/coregentdevspace-youtube-scraper/mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/coregentdevspace-youtube-scraper/mcp.json
- HTML version of this page: https://verifymcp.io/servers/coregentdevspace-youtube-scraper/mcp
