Captapi
REMOTE · API.CAPTAPI.COM · 2 COMPONENTS
Public social media data: profiles, posts, comments, transcripts and ad libraries, 30+ platforms.
Available components
Last scanned (1 hour ago)
Scores higher than 96% of remote servers
Unreachable for 1 day in a row. Last reached 4 Nov 2026.
Category News and Social
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. How we score → Why this is hard to score →
Endpoint Security11
- TLS not yet verified: we couldn't open a connection to check the certificate. View diagnostics → Unverified
- Authorisation not yet verified: we couldn't confirm whether this endpoint requires it. View diagnostics → Unverified
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS not yet verified: we couldn't read the response headers to check for it. View diagnostics → Unverified
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability0
- Transport check failed: declared streamable-http, but we couldn't connect to verify it. See how to fix → View diagnostics → Fail
Schema Quality & AI Usability0
- Schema not yet verified: we couldn't read the endpoint's schema, or could read only part of its tool list.Unverified
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage0
- Tool coverage not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.Unverified
Tool Safety0
- Tool safety not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.Unverified
Capabilities0
- Capabilities not yet verified: we couldn't read the endpoint's capabilities.Unverified
Unverified: 5 categories
Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 5 Nov 26 0
- Endpoint reachability: reachable → unreachable ▼ security
- Stability: fail → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- HSTS header: fail → unverified ▼ security
- Authorization: pass → unverified ▼ security
- TLS certificate: pass → unverified ▼ security
- Transport: pass → fail ▼ security
- Capabilities: fail → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- First check of Schema quality: unverified functional
- 31 Oct 26 0
- Tool “facebook_ad_library_company_ads” rewrote its description, which is the text the model reads security
- “facebook_ad_library_company_ads” added an optional parameter “start_date” cosmetic
- “facebook_ad_library_company_ads” added an optional parameter “sort_by” cosmetic
- “facebook_ad_library_company_ads” added an optional parameter “end_date” cosmetic
- “rumble_channel_videos” reworded the description of “url” cosmetic
- “facebook_ad_library_search” reworded the description of “end_date” cosmetic
- “facebook_ad_library_search” reworded the description of “start_date” cosmetic
- 29 Oct 26 +13
- Authorization: unverified → pass ▲ security
- First check of Authorization: partial security
- The server rewrote its instructions, which are the text every model session reads security
- 26 Oct 26 0
- Tool “pinterest_search” rewrote its description, which is the text the model reads security
- “pinterest_search” reworded the description of “cursor” cosmetic
- “pinterest_search” reworded the description of “limit” cosmetic
- 25 Oct 26 0
- Tool “threads_post_details” rewrote its description, which is the text the model reads security
- Tool “kick_clip” rewrote its description, which is the text the model reads security
- Tool “threads_profile” rewrote its description, which is the text the model reads security
- “kick_clip” reworded the description of “limit” cosmetic
- “threads_user_posts” reworded the description of “limit” cosmetic
- 23 Oct 26 0
- “facebook_marketplace_search” reworded the description of “cursor” cosmetic
- “google_maps_business_search” reworded the description of “limit” cosmetic
- “facebook_marketplace_search” reworded the description of “details” cosmetic
3 cosmetic changes on this day. Switch on “Show cosmetic changes” to see them.
- 20 Oct 26 0
- Tool “tiktok_channel_posts” rewrote its description, which is the text the model reads security
- Tool “threads_user_posts” rewrote its description, which is the text the model reads security
- Tool “linkedin_ad_library_search_ads” rewrote its description, which is the text the model reads security
- Tool “youtube_comments” rewrote its description, which is the text the model reads security
- Tool “youtube_search” rewrote its description, which is the text the model reads security
- “tiktok_popular_creators” reworded the description of “follower_count” cosmetic
- “tiktok_channel_posts” reworded the description of “limit” cosmetic
- “youtube_search” reworded the description of “sortBy” cosmetic
- “tiktok_search_users” reworded the description of “fallback” cosmetic
- “tiktok_search_by_hashtag” reworded the description of “region” cosmetic
- 19 Oct 26 0
- Tool “linkedin_company” rewrote its description, which is the text the model reads security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Probed https://api.captapi.com/mcp
TLS unreached
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of api.captapi.com. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| com. | present | 19718 | 13 | Verified |
| captapi.com. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication Inconclusive
We could not reach the endpoint well enough to judge its authorisation posture.
| Result | Inconclusive |
|---|
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://api.captapi.com/mcp | Unreachable | ||
| http (plaintext) | http://api.captapi.com/mcp | HTTPS enforced |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
twitter_transcript ~153
Tweet text as a transcript — timingSource none (not speech-to-text). Flat 1 credit. Costs 1 credit. Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).
| Name | Type | Req | Description |
|---|---|---|---|
| cache | boolean | – | Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh. |
| url | string | yes | Public tweet URL, e.g. https://x.com/user/status/ID. The URL platform must match this endpoint's platform. Do not pass cross-platform URLs, e.g. YouTube to TikTok, Instagram to Facebook, LinkedIn to… |
No output schema declared.
No examples provided.
twitter_tweet_details ~160
One tweet as JSON — text, author (followers), likes/replies/retweets/quotes, media, ISO publishedAt. Costs 1 credit. Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).
| Name | Type | Req | Description |
|---|---|---|---|
| cache | boolean | – | Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh. |
| url | string | yes | Public tweet URL, e.g. https://x.com/user/status/ID. The URL platform must match this endpoint's platform. Do not pass cross-platform URLs, e.g. YouTube to TikTok, Instagram to Facebook, LinkedIn to… |
No output schema declared.
No examples provided.
twitter_user_tweets ~201
Most popular public tweets from a Twitter/X profile (~100 cap) — not chronological. Text, author, engagement, hashtags, media. Flat 2 credits. Costs 2 credits. Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).
| Name | Type | Req | Description |
|---|---|---|---|
| cache | boolean | – | Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh. |
| limit | integer | – | Max tweets to return (default 20, max 200). Twitter's public surface usually caps around ~100 most popular posts — not chronological latest. Flat 2 credits per call. |
| url | string | yes | Twitter/X profile URL or @handle. The URL platform must match this endpoint's platform. Do not pass cross-platform URLs, e.g. YouTube to TikTok, Instagram to Facebook, LinkedIn to X/Twitter, or Pinte… |
No output schema declared.
No examples provided.
video_summarize ~164
AI transcription + summary of an uploaded file — transcript included; 1 credit/min + 1. Costs 1 credit/min +1. Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).
| Name | Type | Req | Description |
|---|---|---|---|
| file | string | yes | Video or audio file (multipart form field — use -F file=@path, not a query string). Max 200MB / 60 minutes. |
| language | string | – | ISO-639-1 language hint, e.g. "en" or "tr". Omit to auto-detect. |
| timestampGranularity | string | – | segment (default) or word. |
| translate | boolean | – | When true, translate speech to English before summarizing. Default false. |
No output schema declared.
No examples provided.
video_transcript ~173
AI transcription of an uploaded file — 1 credit/min; noSpeech=true and 0 credits when there is no speech. Costs 1 credit/min. Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).
| Name | Type | Req | Description |
|---|---|---|---|
| file | string | yes | Video or audio file (multipart form field — use -F file=@path, not a query string). Max 200MB / 60 minutes. |
| language | string | – | ISO-639-1 language hint, e.g. "en" or "tr". Omit to auto-detect. |
| timestampGranularity | string | – | segment (default) or word — word-level timings when the transcription model exposes them. |
| translate | boolean | – | When true, translate speech to English. Default false. |
No output schema declared.
No examples provided.
youtube_audio_transcript ~271
Speech-to-text for YouTube audio. Use it when a video has no captions — or when you want a transcript of what was actually spoken rather than YouTube's published captions. Priced per started minute of audio. Costs 2 credits/min of audio. Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).
| Name | Type | Req | Description |
|---|---|---|---|
| cache | boolean | – | Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh. |
| language | string | – | Preferred caption language as an ISO code, e.g. "en". Defaults to auto-detect. |
| maxCredits | integer | – | Refuse before STT when estimatedCredits would exceed this (400 cost_exceeds_max, 0 credits). The estimate is on every success and, when the extract miss is retryable, as estimatedCreditsIfRetried. |
| url | string | yes | Public YouTube video URL, e.g. https://youtube.com/watch?v=ID. Not a TikTok/Instagram/Facebook URL. The URL platform must match this endpoint's platform. Do not pass cross-platform URLs, e.g. YouTube… |
No output schema declared.
No examples provided.
youtube_channel_details ~180
YouTube channel stats — ISO country, createdAt date-only, real banner or null, quote-aware SEO tags, absolute links. Flat 1 credit. Costs 1 credit. Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).
| Name | Type | Req | Description |
|---|---|---|---|
| cache | boolean | – | Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh. |
| url | string | yes | YouTube channel URL, @handle, bare handle, or UC... channel ID, e.g. https://youtube.com/@handle or @mkbhd. The URL platform must match this endpoint's platform. Do not pass cross-platform URLs, e.g.… |
No output schema declared.
No examples provided.
youtube_channel_playlists ~226
Channel playlists with cursor pagination — id, title, totalVideos, thumbnailUrl. Flat 2 credits/page. Costs 2 credits. Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).
| Name | Type | Req | Description |
|---|---|---|---|
| cache | boolean | – | Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh. |
| cursor | string | – | Pagination cursor. Leave empty for the first page; then pass the nextCursor value returned in the previous response. |
| limit | integer | – | Max items to return (default 20, max 200). Flat 2 credits per call. |
| url | string | yes | YouTube channel URL, @handle, bare handle, or UC... channel ID, e.g. https://youtube.com/@handle or @mkbhd. The URL platform must match this endpoint's platform. Do not pass cross-platform URLs, e.g.… |
No output schema declared.
No examples provided.
youtube_channel_shorts ~222
Channel Shorts with cursor pagination — same row shape as channel-videos (exact publishedAt). Costs 2 credits. Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).
| Name | Type | Req | Description |
|---|---|---|---|
| cache | boolean | – | Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh. |
| cursor | string | – | Pagination cursor. Leave empty for the first page; then pass the nextCursor value returned in the previous response. |
| limit | integer | – | Max items to return (default 20, max 200). Flat 2 credits per call. |
| url | string | yes | YouTube channel URL, @handle, bare handle, or UC... channel ID, e.g. https://youtube.com/@handle or @mkbhd. The URL platform must match this endpoint's platform. Do not pass cross-platform URLs, e.g.… |
No output schema declared.
No examples provided.
youtube_channel_streams ~210
Channel Live tab only — liveStatus per row; 0 credits when hasLiveTab is false. Costs 2 credits. Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).
| Name | Type | Req | Description |
|---|---|---|---|
| cache | boolean | – | Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh. |
| limit | integer | – | Max items to return (default 20, max 200). Flat 2 credits when hasLiveTab is true; 0 credits when hasLiveTab is false. |
| url | string | yes | YouTube channel URL, @handle, bare handle, or UC... channel ID, e.g. https://youtube.com/@handle or @mkbhd. The URL platform must match this endpoint's platform. Do not pass cross-platform URLs, e.g.… |
No output schema declared.
No examples provided.
youtube_channel_videos ~255
Channel uploads with cursor pagination — exact publishedAt from reel_item_watch (same as channel-shorts). Costs 2 credits. Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).
| Name | Type | Req | Description |
|---|---|---|---|
| cache | boolean | – | Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh. |
| cursor | string | – | Pagination cursor. Leave empty for the first page; then pass the nextCursor value returned in the previous response. |
| fast | boolean | – | Set true to use YouTube RSS for faster results with less detailed metadata. Leave false when viewCount/duration quality matters. |
| limit | integer | – | Max items to return (default 20, max 200). Flat 2 credits per call. |
| url | string | yes | YouTube channel URL, @handle, bare handle, or UC... channel ID, e.g. https://youtube.com/@handle or @mkbhd. The URL platform must match this endpoint's platform. Do not pass cross-platform URLs, e.g.… |
No output schema declared.
No examples provided.
youtube_comment_replies ~252
Replies under a top-level comment — parentReplyCount + cursor. Nested reply ids return 404. Costs 2 credits. Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).
| Name | Type | Req | Description |
|---|---|---|---|
| cache | boolean | – | Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh. |
| commentId | string | yes | ID of the parent (top-level) comment to fetch replies for — from the comments endpoint. Legacy alias: comment_id. |
| cursor | string | – | Pagination cursor. Leave empty for the first page; then pass the nextCursor value returned in the previous response. |
| limit | integer | – | Max items to return (default 50, max 500). Flat 2 credits per call. |
| url | string | yes | Public YouTube video URL, e.g. https://youtube.com/watch?v=ID. Not a TikTok/Instagram/Facebook URL. The URL platform must match this endpoint's platform. Do not pass cross-platform URLs, e.g. YouTube… |
No output schema declared.
No examples provided.
youtube_comments ~254
Get comments on any YouTube video — text, author, likes, and truncated publishedTimeApprox from the relative label, with cursor pagination (nextCursor + hasMore). Flat 2 credits per call; 0 when the video has comments turned off (commentsDisabled: true). Costs 2 credits. Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).
| Name | Type | Req | Description |
|---|---|---|---|
| cache | boolean | – | Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh. |
| cursor | string | – | Pagination cursor. Leave empty for the first page; then pass the nextCursor value returned in the previous response. |
| limit | integer | – | Max items to return (default 50, max 500). Flat 2 credits per call. |
| url | string | yes | Public YouTube video URL, e.g. https://youtube.com/watch?v=ID. Not a TikTok/Instagram/Facebook URL. The URL platform must match this endpoint's platform. Do not pass cross-platform URLs, e.g. YouTube… |
No output schema declared.
No examples provided.
youtube_community_post_details ~157
One community post — list schema + commentCount trio + isEdited. Costs 1 credit. Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).
| Name | Type | Req | Description |
|---|---|---|---|
| cache | boolean | – | Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh. |
| url | string | yes | YouTube community post URL (/post/Ugkx… or /community?lb=). Trailing whitespace is stripped. The URL platform must match this endpoint's platform. Do not pass cross-platform URLs, e.g. YouTube to Tik… |
No output schema declared.
No examples provided.
youtube_community_posts ~227
Community posts — channel{}, publishedTimeApprox, likeCountIsApproximate, linkedVideos[], cursor (1 credit). Costs 1 credit. Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).
| Name | Type | Req | Description |
|---|---|---|---|
| cache | boolean | – | Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh. |
| cursor | string | – | Pagination cursor. Leave empty for the first page; then pass the nextCursor value returned in the previous response. |
| limit | integer | – | Max items to return (default 20, max 200). Flat 1 credit per call. |
| url | string | yes | YouTube channel URL, @handle, bare handle, or UC... channel ID, e.g. https://youtube.com/@handle or @mkbhd. The URL platform must match this endpoint's platform. Do not pass cross-platform URLs, e.g.… |
No output schema declared.
No examples provided.
youtube_hashtag_search ~167
Videos from youtube.com/hashtag/{name} — nested channel{}, viewCountIsApproximate. Not keyword search. Costs ~20 credits (1/result). Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).
| Name | Type | Req | Description |
|---|---|---|---|
| cache | boolean | – | Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh. |
| limit | integer | – | Max items to return (default 20, max 200). Returns a single window; use limit to size it. No cursor. Billed per result. |
| q | string | yes | Hashtag with or without the # (min 2 characters). One token — spaces are 400 HASHTAG_HAS_SPACES. |
No output schema declared.
No examples provided.
youtube_playlist ~157
Playlist metadata only — title, channel{}, totalVideos, thumbnailUrl. No videos[]. Flat 1 credit. Costs 1 credit. Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).
| Name | Type | Req | Description |
|---|---|---|---|
| cache | boolean | – | Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh. |
| url | string | yes | YouTube playlist URL, e.g. https://youtube.com/playlist?list=ID. The URL platform must match this endpoint's platform. Do not pass cross-platform URLs, e.g. YouTube to TikTok, Instagram to Facebook,… |
No output schema declared.
No examples provided.
youtube_playlist_videos ~249
Paginated playlist contents — cursor/nextCursor/hasMore, same row shape as channel-videos. Flat 2 credits/page. Costs 2 credits. Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).
| Name | Type | Req | Description |
|---|---|---|---|
| cache | boolean | – | Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh. |
| cursor | string | – | Pagination cursor. Leave empty for the first page; then pass the nextCursor value returned in the previous response. |
| fast | boolean | – | Set true to use YouTube RSS for faster results with less detailed metadata. Leave false when viewCount/duration quality matters. |
| limit | integer | – | Max items to return (default 50, max 500). Flat 2 credits per call. |
| url | string | yes | YouTube playlist URL, e.g. https://youtube.com/playlist?list=ID. The URL platform must match this endpoint's platform. Do not pass cross-platform URLs, e.g. YouTube to TikTok, Instagram to Facebook,… |
No output schema declared.
No examples provided.
youtube_search ~303
YouTube search with cursor pagination — typed hits, ids, canonical URLs, filters (2 credits/page, 0 when a page finds nothing). Costs 2 credits. Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).
| Name | Type | Req | Description |
|---|---|---|---|
| cache | boolean | – | Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh. |
| cursor | string | – | Pagination cursor. Leave empty for the first page; then pass the nextCursor value returned in the previous response. |
| duration | string | – | any | under_4 | 4_20 | over_20. Applies to long-form videos (not Shorts). |
| limit | integer | – | Max items to return (default 20, max 200). Flat 2 credits per call. |
| q | string | yes | Search query or keywords (min 2 characters). |
| region | string | – | ISO country code for localized results (default US). |
| sortBy | string | – | relevance | views (alias: popular→views). date and rating answer 400 SORT_NOT_SUPPORTED: YouTube no longer orders search by upload date (use uploadDate) or by rating. With type=shorts only relevance… |
| type | string | – | all | videos | shorts | channels | playlists. |
| uploadDate | string | – | any | today | this_week | this_month | this_year. |
No output schema declared.
No examples provided.
youtube_shorts_comments ~233
Comments on a YouTube Short — rejects long-form videos (≤3 min only). Costs 2 credits. Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).
| Name | Type | Req | Description |
|---|---|---|---|
| cache | boolean | – | Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh. |
| cursor | string | – | Pagination cursor. Leave empty for the first page; then pass the nextCursor value returned in the previous response. |
| limit | integer | – | Max items to return (default 50, max 500). Flat 2 credits per call. |
| url | string | yes | Public YouTube Shorts URL, e.g. https://youtube.com/shorts/ID (≤3 min). Long-form videos return HTTP 422 — use the matching /v1/youtube/… endpoint instead. The URL platform must match this endpoint's… |
No output schema declared.
No examples provided.
youtube_shorts_details ~186
YouTube Short metadata — same schema as Video Details, with isShort:true; long-form videos get HTTP 422. Costs 1 credit. Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).
| Name | Type | Req | Description |
|---|---|---|---|
| cache | boolean | – | Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh. |
| url | string | yes | Public YouTube Shorts URL, e.g. https://youtube.com/shorts/ID (≤3 min). Long-form videos return HTTP 422 — use the matching /v1/youtube/… endpoint instead. The URL platform must match this endpoint's… |
No output schema declared.
No examples provided.
youtube_shorts_summarize ~208
AI summary of a YouTube Short — rejects long-form videos (≤3 min only). Costs 3 credits. Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).
| Name | Type | Req | Description |
|---|---|---|---|
| cache | boolean | – | Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh. |
| language | string | – | Preferred caption language as an ISO code, e.g. "en". Defaults to auto-detect. |
| url | string | yes | Public YouTube Shorts URL, e.g. https://youtube.com/shorts/ID (≤3 min). Long-form videos return HTTP 422 — use the matching /v1/youtube/… endpoint instead. The URL platform must match this endpoint's… |
No output schema declared.
No examples provided.
youtube_shorts_transcript ~206
Transcript for a YouTube Short — rejects long-form videos (≤3 min only). Costs 1 credit. Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).
| Name | Type | Req | Description |
|---|---|---|---|
| cache | boolean | – | Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh. |
| language | string | – | Preferred caption language as an ISO code, e.g. "en". Defaults to auto-detect. |
| url | string | yes | Public YouTube Shorts URL, e.g. https://youtube.com/shorts/ID (≤3 min). Long-form videos return HTTP 422 — use the matching /v1/youtube/… endpoint instead. The URL platform must match this endpoint's… |
No output schema declared.
No examples provided.
youtube_summarize ~201
AI summary from YouTube's published captions — same source as /transcript. Flat 3 credits; caption-miss 404 is free. Costs 3 credits. Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).
| Name | Type | Req | Description |
|---|---|---|---|
| cache | boolean | – | Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh. |
| language | string | – | Preferred caption language as an ISO code, e.g. "en". Defaults to auto-detect. |
| url | string | yes | Public YouTube video URL, e.g. https://youtube.com/watch?v=ID. Not a TikTok/Instagram/Facebook URL. The URL platform must match this endpoint's platform. Do not pass cross-platform URLs, e.g. YouTube… |
No output schema declared.
No examples provided.
youtube_transcript ~194
YouTube's published captions with timestamps — not speech-to-text. Flat 1 credit; 404 is free. Costs 1 credit. Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).
| Name | Type | Req | Description |
|---|---|---|---|
| cache | boolean | – | Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh. |
| language | string | – | Preferred caption language as an ISO code, e.g. "en". Defaults to auto-detect. |
| url | string | yes | Public YouTube video URL, e.g. https://youtube.com/watch?v=ID. Not a TikTok/Instagram/Facebook URL. The URL platform must match this endpoint's platform. Do not pass cross-platform URLs, e.g. YouTube… |
No output schema declared.
No examples provided.
youtube_trending_shorts ~165
YouTube Shorts recommendation sequence — fixed window per call (no cursor), not a global chart. Costs 2 credits. Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).
| Name | Type | Req | Description |
|---|---|---|---|
| cache | boolean | – | Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh. |
| limit | integer | – | Max items to return (default 20, max 100). Returns a single window; use limit to size it. No cursor. Flat 2 credits per call. |
| q | string | – | Optional topic seed for the Shorts recommendation sequence. Omit (or pass trending/shorts) for the default reel feed — not a keyword search. |
No output schema declared.
No examples provided.
youtube_video_details ~165
YouTube video metadata + stats. Always includes degraded / degradedReason — retry when degraded is true. Costs 1 credit. Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).
| Name | Type | Req | Description |
|---|---|---|---|
| cache | boolean | – | Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh. |
| url | string | yes | Public YouTube video URL, e.g. https://youtube.com/watch?v=ID. Not a TikTok/Instagram/Facebook URL. The URL platform must match this endpoint's platform. Do not pass cross-platform URLs, e.g. YouTube… |
No output schema declared.
No examples provided.
youtube_video_sponsors ~229
SponsorBlock community segments — free while the CC BY-NC-SA commercial-use exception is pending. Costs 0 credits. Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).
| Name | Type | Req | Description |
|---|---|---|---|
| cache | boolean | – | Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh. |
| categories | string | – | Comma-separated categories. Default sponsor,selfpromo,interaction. Also intro,outro,preview,music_offtopic,poi_highlight,filler. |
| minVotes | integer | – | Minimum SponsorBlock votes to keep a segment. Default 0 (drops community-rejected votes < 0). |
| url | string | yes | Public YouTube video URL, e.g. https://youtube.com/watch?v=ID. Not a TikTok/Instagram/Facebook URL. The URL platform must match this endpoint's platform. Do not pass cross-platform URLs, e.g. YouTube… |
No output schema declared.
No examples provided.
How do I install the Captapi MCP server?
Captapi is a hosted endpoint at https://api.captapi.com/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.
remote · api.captapi.com
claude mcp add --transport http cdcstream-captapi 'https://api.captapi.com/mcp'
What is the Captapi MCP server?
Captapi is an MCP server listed in the public MCP registry as io.github.CDCStream/captapi. Public social media data: profiles, posts, comments, transcripts and ad libraries, 30+ platforms. This page covers its hosted endpoint (https://api.captapi.com/mcp).
Is the Captapi MCP server safe to use?
Captapi scores 88 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 Captapi MCP server expose?
Captapi exposes 178 tools: youtube_transcript, youtube_audio_transcript, youtube_summarize, youtube_video_details, youtube_comments, and 173 more. Their descriptions and schemas cost roughly 37,314 tokens of context every time the server is loaded.
Does the Captapi MCP server require authentication?
Its publisher declares that Captapi requires credentials, so you will need to authorise it in your MCP client. We have not been able to confirm that against the live endpoint.
Is the Captapi MCP server still maintained?
Captapi is still listed in the MCP registry, though our most recent checks did not reach this channel. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.