Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

APICK

REMOTE · APICK.APP · 2 COMPONENTS

APICK Korean data, simple-auth lookups, document forms, OCR, search, image, video and TTS

0 this week 78 Trust /100

Last scanned (6 hours ago)

Scores higher than 76% of remote servers

Reachable. Last reached 5 Nov 2026.

Trust breakdown (7 categories)

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 Security63
Transport & Reachability100
Schema Quality & AI Usability66
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 41966 tokens (~187/item across 224 items; 224 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management99
  • Stability check failed: schema churn in the 30 days we've observed: 1 tool removals, 0 breaking changes, 0 auth/transport breaks, 106 additions. See how to fix → Fail
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety90
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 3 of 5 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "pdf_merge" implies "merge" and declares readOnlyHint instead, contradicting what its own name says it does. See how to fix → Partial
  • An AI judge read all 224 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
What we tested

Checks we ran (13)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

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
    • New tool “document_workflow_cancel”, which the server declares destructive security
    • New tool “document_attachment_remove”, which the server declares destructive security
    • Tool “form_list” rewrote its description, which is the text the model reads security
    • Tool “form_document” rewrote its description, which is the text the model reads security
    • Destructive annotations: 50% → 60% ▲ functional
    • New tool “document_download_pdf” functional
    • New tool “document_finalize” functional
    • New tool “document_quota” functional
    • New tool “document_review” functional
    • New tool “document_workflow_start” functional
    • New tool “document_workflow_quote” functional
    • New tool “document_workflow_get” functional
    • New tool “document_workflow_apply” functional
    • New tool “document_workflow_answer” functional
    • New tool “document_verify” functional
    • New tool “document_templates” functional
    • New tool “document_template” functional
    • New tool “document_assist” functional
    • New tool “document_attachment_add” functional
    • New tool “document_attachment_list” functional
    • New tool “document_download_bundle” functional
  • 4 Nov 26 0
    • Tool “registry_realestate_jobs_create” rewrote its description, which is the text the model reads security
    • Tool “google_maps_search” rewrote its description, which is the text the model reads security
    • Tool “registry_corporate_jobs_create” rewrote its description, which is the text the model reads security
  • 3 Nov 26 0
    • New tool “document_delete”, which the server declares destructive security
    • Tool “form_document” rewrote its description, which is the text the model reads security
    • Destructive annotations: 33% → 50% ▲ functional
    • New tool “document_update” functional
    • New tool “document_quote” functional
    • New tool “document_list” functional
    • New tool “document_get” functional
    • New tool “document_download” functional
    • New tool “document_ai_write” functional
    • New tool “document_create” functional
    • New tool “form_ai_fill” functional
    • New tool “form_bundle” functional
    • New tool “form_preview” functional
    • New tool “form_list” functional
    • New tool “form_fields” functional
    • New tool “form_document” functional
    • “form_document” added an optional parameter “stamp_image” cosmetic
    • “form_document” added an optional parameter “signature_image” cosmetic
  • 2 Nov 26 0
    • New tool “dart_disclosure” functional
    • New tool “dart_company” functional
    • New tool “dart_financials” functional
    • “kling_jobs_create” added an optional parameter “reference_image_url_10” cosmetic
    • “kling_jobs_create” added an optional parameter “reference_image_url_8” cosmetic
    • “kling_jobs_create” added an optional parameter “reference_image_url_9” cosmetic
    • “kling_jobs_create” added an optional parameter “reference_video_url_5” cosmetic
    • “kling_jobs_create” reworded the description of “duration” cosmetic
  • 1 Nov 26 0
    • Tool “instagram_profile” rewrote its description, which is the text the model reads security
    • New tool “url_to_markdown” functional
    • New tool “web_capture_extract” functional
    • New tool “email_risk_batch” functional
    • New tool “crypto_market” functional
  • 29 Oct 26 0
    • Tool “get_pccc” rewrote its description, which is the text the model reads security
    • Tool “req_pccc” rewrote its description, which is the text the model reads security
    • New tool “get_hometax_bundle” functional
    • New tool “get_nps_bundle” functional
    • New tool “req_hometax_biz_bundle” functional
    • New tool “req_hometax_bundle” functional
    • New tool “req_nps_bundle” functional
    • New tool “get_hometax_biz_bundle” functional
  • 28 Oct 26 0
    • Tool “google_shopping_search” rewrote its description, which is the text the model reads security
    • Tool “land_rt_price” rewrote its description, which is the text the model reads security
    • Tool “app_reviews” rewrote its description, which is the text the model reads security
    • Tool “corp_finance” rewrote its description, which is the text the model reads security
    • Tool “google_image_search” rewrote its description, which is the text the model reads security
    • Tool “google_maps_search” rewrote its description, which is the text the model reads security
    • Tool “google_news_search” rewrote its description, which is the text the model reads security
    • Tool “google_rank_check” rewrote its description, which is the text the model reads security
    • Tool “google_search” rewrote its description, which is the text the model reads security
    • New tool “geo_address_cleanup” functional
    • New tool “land_info” functional
    • New tool “geo_site_score” functional
  • 25 Oct 26 0
    • Tool “court_auction” rewrote its description, which is the text the model reads security
Diagnostics

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://apick.app/mcp/all

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=apick.app CN=YE2,O=Let's Encrypt,C=US 21 Sept 2026 20 Dec 2026 ECDSA 256 ECDSA-SHA384 6df569e0949f856521f576f0e936f1ae953
SANs: apick.app
CN=YE2,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 4df3b15dd6c0784c507cd37b58e6f115
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of apick.app. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
app. DS published 23684 8 Verified
apick.app. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=15552000
content-security-policy frame-ancestors 'self'
x-content-type-options nosniff
x-frame-options SAMEORIGIN
referrer-policy strict-origin-when-cross-origin

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://apick.app/mcp/all Verified 200
http (plaintext) http://apick.app/mcp/all HTTPS enforced 308 https://apick.app/mcp/all
MCP tools · 224 exposed · ~41,966 tokens

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 →

Tool Tokens
url_to_markdown ~140

Return the main content of a web page as clean Markdown and structured JSON (headings, links, images, plain text). 임의의 웹페이지에서 메뉴·광고·각주를 걷어 낸 본문을 Markdown 또는 JSON 으로 정리합니다. 문서 정리·RAG 입력 만들기에 사용합니다. [호출당 15포인트]

NameTypeReqDescription
formatstring–markdown · json · both(기본)
max_charsinteger–본문 최대 글자 수 (기본 100000)
urlstringyes변환할 페이지 주소 (http·https)

No output schema declared.

No examples provided.

vehicle_emission ~143

Look up Korean vehicle emission certification details by emission certification number. 배출가스인증번호로 인증일·차명·제조사·제작국가·연료·배출가스차종·배기량·엔진출력·변속기·공차중량·총중량과 인증 이력을 조회합니다. 입력은 차량번호가 아니라 배출가스인증번호이며, 배출가스 등급은 제공하지 않습니다. [호출당 60포인트]

NameTypeReqDescription
cert_nostringyes배출가스인증번호. 예: KMY-SY-13-24

No output schema declared.

No examples provided.

vehicle_model_info ~468

Look up specifications of a Korean-market vehicle model (passenger cars and motorcycles/scooters) by brand, model name, model year and trim. 브랜드·차명·연식·등급으로 해당 차종(승용차와 오토바이·스쿠터 같은 이륜차)의 제원(배기량·연비·치수·타이어·소모품 규격 등), 사양, 등급 후보를 조회합니다. 차명 없이 부르면 브랜드·차종 목록을 돌려줍니다. 차명·등급 표기가 달라도 가장 비슷한 차종을 찾아 주며, 확신이 높으면 그 차종의 제원과 함께 추천(추천.자동선택, 추천.대안)을 알려주고 확신이 낮으면 제원 없이 후보만 알려줍니다. 제원 값은 표준 표기로만 내려갑니다(연료: 가솔린·디젤·LPG·전기·수소·하이브리드, 차체형상: 세단·SUV·MPV·스쿠터·네이키드 등, 구동방식: 전륜·후륜·2WD·AWD, 변속기: 자동 8단·DCT 7단·CVT, 에너지효율등급: 1~5등급, 여러 값은 "+"로 연결). [호출당 20포인트]

NameTypeReqDescription
makerstring–브랜드. 예: 현대, 기아, BMW, 렉서스
modelstring–차명 또는 자유문 검색어. 예: 파나메라 gts 4인승 19년식, PANAMERA GTS 19년, 더 뉴 K5. 차명·연식·등급·승차인원을 비교하며 적합한 제원이 없으면 미과금. 비우면 차종 목록
modelYearstring–연식. 예: 2024, 24년식. model에 포함 가능하며 별도 값과 다르면 입력 오류
trimstring–등급·트림. 예: 프레스티지

No output schema declared.

No examples provided.

vehicle_recall ~167

Check whether a Korean vehicle is subject to recalls or free repair campaigns by plate number or VIN. 차량번호 또는 차대번호(VIN) 중 하나로 리콜·무상점검수리 대상 여부와 건수, 리콜별 내용·시정 기간을 조회합니다. 리콜 대상이 아니면(recall_target=false) 과금되지 않습니다. car_no 와 vin 은 둘 중 하나만 보냅니다. [호출당 60포인트]

NameTypeReqDescription
car_nostring–차량번호. 예: 12가3456, 서울12가3456 (vin 과 함께 보내지 않는다)
vinstring–차대번호 17자리. 예: KMHXX00XXXX000000 (car_no 와 함께 보내지 않는다)

No output schema declared.

No examples provided.

vehicle_tax_calc ~177

Calculate the annual Korean automobile tax for a non-commercial passenger car from engine displacement and vehicle age. 비영업용 승용자동차의 배기량(cc)과 차령으로 연간 자동차세·지방교육세·합계를 계산합니다. 차령 3년차부터 매년 5%씩 최대 50%까지 경감합니다. 연납 공제·감면·영업용 차량은 계산하지 않습니다. [호출당 60포인트]

NameTypeReqDescription
car_age_yearsinteger–차령(년), 0~40. 생략하면 0
ccintegeryes배기량(cc), 50~10000
yearinteger–과세연도(YYYY), 2011년부터 올해까지. 생략하면 올해

No output schema declared.

No examples provided.

venture_biz_info ~96

Look up venture company information of a Korean business, including financial statements and investment data. 벤처기업을 대상으로 사업자 정보, 대차대조표, 손익계산서, 투자정보, 벤처기업확인정보를 조회합니다. [호출당 40포인트]

NameTypeReqDescription
biz_nostringyes사업자등록번호 (숫자 10자리, 하이픈 제외)

No output schema declared.

No examples provided.

veo_jobs_create ~765

Submit an asynchronous Veo video generation job. Select version and tier; supported modes, durations and prices depend on the selected version. Veo 영상 생성 작업을 비동기로 접수합니다. text/image/reference 세 가지 mode를 지원하며, veo_jobs_status Tool로 상태를 조회하고 완료되면 응답의 result_url(REST 다운로드 주소, 7일 이내 유효)로 다운로드합니다. 접수 시 duration × 초당 900포인트가 예약 차감되고 완료 시 확정, 실패·시간 초과 시 전액 환불됩니다. [기본 버전 기준: 초당 900포인트 × duration(초). 다른 버전은 개발가이드의 버전별 요금표 참고.]

NameTypeReqDescription
aspect_ratiostring–출력 화면 비율. 선택 버전·등급·모드에서 허용하는 값만 사용하세요.
audioboolean–오디오 생성 여부. 선택 가능한 버전은 기본 true, 무음 전용 버전은 false, 오디오 필수 버전은 true만 허용합니다.
durationinteger–영상 길이(초), 전체 버전 범위 4~8. 허용 값과 기본값은 버전·등급별로 다릅니다.
idempotency_keystring–같은 요청의 재전송으로 인한 중복 접수·과금을 막는 고유 키
image_urlstring–image 모드에서 사용할 첫 프레임 이미지 URL — 다운로드 가능한 https URL (허용 형식: image/png, image/jpeg, image/webp) (최대 50MB)
last_image_urlstring–image 모드에서 사용할 마지막 프레임 이미지 URL(선택) — 다운로드 가능한 https URL (허용 형식: image/png, image/jpeg, image/webp) (최대 50MB)
modestring–입력 방식 — 'text'(텍스트만) | 'image'(첫 프레임 이미지 지정) | 'reference'(참조 이미지·영상으로 주체 지정). 기본 text
negative_promptstring–제외할 요소를 설명하는 텍스트
promptstringyes영상 생성 프롬프트, 최대 2,000자
reference_image_urlstring–reference 모드에서 주체를 지정할 참조 이미지 URL — 다운로드 가능한 https URL (허용 형식: image/png, image/jpeg, image/webp) (최대 50MB)
reference_image_url_2string–reference 모드 참조 이미지 URL(2번째) — 다운로드 가능한 https URL (허용 형식: image/png, image/jpeg, image/webp) (최대 50MB)
reference_image_url_3string–reference 모드 참조 이미지 URL(3번째) — 다운로드 가능한 https URL (허용 형식: image/png, image/jpeg, image/webp) (최대 50MB)
resolutionstring–출력 해상도. 전체 버전의 값 목록이며 허용 조합·기본값·요금은 버전별 개발가이드를 따릅니다.
seedinteger–재현성을 위한 시드 값
tierstring–품질·속도 등급. 지원 등급과 생략 시 기본값은 version과 mode에 따라 다릅니다.
versionstring–영상 모델 버전. 생략 시 3.1. 등급·해상도·길이·오디오·파일 제약과 요금은 선택 버전별 개발가이드 표를 확인하세요.

No output schema declared.

No examples provided.

veo_jobs_status ~81

Check the status of a Veo video generation job submitted via veo_jobs_create. Veo 영상 작업의 진행 상태를 조회합니다. 완료되면 응답의 result_url(REST 다운로드 주소)로 안내하며, 결과는 완료 후 7일간 유효합니다. 무료입니다. [무료]

NameTypeReqDescription
job_idstringyes작업 ID

No output schema declared.

No examples provided.

video_to_mp3 ~99

Extract the audio track of a video file as an MP3 file. 동영상 파일에서 오디오를 추출해 MP3 파일로 반환합니다. [호출당 30포인트]

NameTypeReqDescription
video_urlstringyes다운로드 가능한 https URL (허용 형식: video/mp4, video/quicktime, video/x-msvideo, video/webm, video/x-matroska) (최대 200MB)

No output schema declared.

No examples provided.

voice_change ~183

Modulate the voice in a video or audio file to a lower or higher pitch. 동영상 또는 오디오 파일의 음성을 저음 또는 고음으로 변조합니다. MP3, WAV 등 오디오와 MP4, MOV 등 동영상 포맷을 지원하며, 변조된 파일을 반환합니다. [호출당 10포인트]

NameTypeReqDescription
media_urlstringyes다운로드 가능한 https URL (허용 형식: audio/mpeg, audio/mp3, audio/wav, audio/x-wav, audio/mp4, audio/aac, audio/ogg, video/mp4, video/quicktime, video/x-msvideo, video/x-matroska, video/webm) (최대 200MB)
typestringyes변조음 타입 (1: 저음, 2: 고음)

No output schema declared.

No examples provided.

web_capture_extract ~104

Capture a full-page screenshot and return the on-screen text blocks with their x/y/width/height coordinates. 웹페이지 전체 화면 이미지와 화면에 보이는 제목·문단·목록·표의 글자와 위치를 함께 반환합니다. 이미지 위에 글자 위치를 표시하거나 화면 구성을 분석할 때 사용합니다. [호출당 20포인트]

NameTypeReqDescription
urlstringyes캡처할 페이지 주소 (http·https)

No output schema declared.

No examples provided.

whois ~98

WHOIS lookup for a domain or IP address, returning registration and ownership information. 특정 도메인 또는 IP의 WHOIS(등록·소유) 정보를 조회합니다. .kr/.한국 도메인, 국내 IP, AS번호(예: AS9318)도 조회할 수 있습니다. [호출당 100포인트]

NameTypeReqDescription
addressstringyes검색할 도메인 또는 IP (예: apick.app)

No output schema declared.

No examples provided.

word_cloud ~93

Generate a word cloud image (JPEG) from input text, sizing each word by frequency. 입력 텍스트를 구성하는 단어의 중요도(빈도수)에 따라 서로 다른 크기의 단어로 이루어진 워드클라우드 이미지(JPEG)를 생성해 반환합니다. [호출당 10포인트]

NameTypeReqDescription
textstringyes워드클라우드를 생성할 텍스트

No output schema declared.

No examples provided.

x_post ~106

X (Twitter) post by URL: text, time, likes, reposts, replies, views, hashtags and media URLs. X 게시물 주소로 본문·작성 시각·좋아요·리포스트·답글·조회수·해시태그·미디어 주소를 조회합니다. [호출당 10포인트]

NameTypeReqDescription
urlstringyesX 게시물 주소 (예: https://x.com/NASA/status/1234567890)

No output schema declared.

No examples provided.

x_profile ~117

X (Twitter) public profile: followers, following, posts count, bio, verification and recent posts with engagement. X 공개 계정의 팔로워·팔로잉·게시물 수·소개·인증 여부와 최근 게시물 반응 지표를 조회합니다. [호출당 20포인트]

NameTypeReqDescription
urlstring–X 프로필 주소 (예: https://x.com/NASA)
usernamestring–X 사용자명 (@ 없이도 가능, username 또는 url 중 하나 필수)

No output schema declared.

No examples provided.

youtube_channel ~143

Look up a YouTube channel (name, handle, subscribers, description) and list items of its videos, shorts, live or playlists tab. 유튜브 채널의 이름·핸들·구독자 수·소개와 영상·쇼츠·라이브·재생목록 탭의 목록을 조회합니다. [호출당 20포인트]

NameTypeReqDescription
channelstringyes채널 URL, 핸들(@이름) 또는 채널 ID(UC...)
countinteger–받을 항목 수 1~100 (기본 30)
tabstring–목록 탭 (기본 videos)

No output schema declared.

No examples provided.

youtube_comments ~151

List comments of a public YouTube video sorted by top or newest, with author, text, likes, pinned/hearted flags and optional replies. 유튜브 공개 영상의 댓글을 인기순 또는 최신순으로 조회합니다. [호출당 30포인트]

NameTypeReqDescription
countinteger–받을 댓글 수 1~200 (기본 20, 답글 포함)
repliesboolean–true면 댓글마다 답글을 최대 5개까지 함께 받습니다 (기본 false)
sortstring–top(인기순, 기본)·new(최신순)
urlstringyes유튜브 영상 URL 또는 11자리 영상 ID

No output schema declared.

No examples provided.

youtube_hashtag ~83

List videos on a YouTube hashtag page. 유튜브 해시태그 페이지에 올라온 영상 목록을 조회합니다. [호출당 20포인트]

NameTypeReqDescription
countinteger–받을 영상 수 1~100 (기본 30)
hashtagstringyes해시태그 (# 생략 가능, 예: kpop)

No output schema declared.

No examples provided.

youtube_metadata ~131

Look up metadata of a public YouTube video: title, channel, duration, views, likes, upload date, description, tags, chapters and thumbnails. 유튜브 공개 영상의 제목·채널·길이·조회수·좋아요·업로드일·설명·태그·챕터·썸네일 목록을 조회합니다. [호출당 20포인트]

NameTypeReqDescription
urlstringyes유튜브 영상 URL 또는 11자리 영상 ID (예: https://www.youtube.com/watch?v=..., https://youtu.be/..., /shorts/...)

No output schema declared.

No examples provided.

youtube_playlist ~109

Look up a public YouTube playlist: title, channel, video count and the list of videos in it. 유튜브 공개 재생목록의 제목·채널·영상 수와 수록 영상 목록을 조회합니다. [호출당 20포인트]

NameTypeReqDescription
countinteger–받을 영상 수 1~200 (기본 50)
urlstringyes재생목록 URL(list= 포함) 또는 재생목록 ID (예: PL...)

No output schema declared.

No examples provided.

youtube_search ~215

Search YouTube by keyword and list videos, shorts, channels or playlists with title, channel, duration, views and thumbnail. Supports sort (relevance, date, views, rating) and filters (upload date, type, duration). 키워드로 유튜브 영상·쇼츠·채널·재생목록을 검색합니다. [호출당 20포인트]

NameTypeReqDescription
countinteger–결과 수 1~50 (기본 10)
durationstring–길이: short(4분 미만)·medium(4~20분)·long(20분 초과)
querystringyes검색어 (1~200자)
sortstring–정렬: relevance(관련도, 기본)·date(업로드일)·views(조회수)·rating(평점)
typestring–결과 종류 (기본 any)
upload_datestring–업로드 시기 (기본 any)

No output schema declared.

No examples provided.

youtube_subtitle ~217

Download the subtitles of a public YouTube video in one language as VTT, SRT or plain text. 유튜브 공개 영상의 자막을 언어별로 VTT·SRT·텍스트 파일로 내려받습니다. 제공 언어는 youtube_subtitle_list로 확인합니다. [호출당 30포인트]

NameTypeReqDescription
formatstring–파일 형식 vtt(기본)·srt·txt. txt는 시간 정보를 뺀 본문만 반환합니다.
langstringyes자막 언어 코드 (예: ko, en, en-US, en-orig). 자막 목록 조회 결과의 lang 값. 자동 번역 자막(translated=true)은 실패할 수 있어 원어 자막을 권장
typestring–자막 종류 any(기본: 수동 자막 우선, 없으면 자동 생성)·manual·auto
urlstringyes유튜브 영상 URL 또는 11자리 영상 ID

No output schema declared.

No examples provided.

youtube_subtitle_list ~78

List the manual and auto-generated subtitle languages available for a public YouTube video. 유튜브 공개 영상에서 제공하는 수동 자막과 자동 생성 자막의 언어 목록을 조회합니다. [호출당 20포인트]

NameTypeReqDescription
urlstringyes유튜브 영상 URL 또는 11자리 영상 ID

No output schema declared.

No examples provided.

youtube_thumbnail ~71

Download the largest thumbnail of a public YouTube video as a JPG image. 유튜브 공개 영상의 가장 큰 썸네일 이미지를 JPG 파일로 내려받습니다. [호출당 20포인트]

NameTypeReqDescription
urlstringyes유튜브 영상 URL 또는 11자리 영상 ID

No output schema declared.

No examples provided.

Install

How do I install the APICK MCP server?

APICK is a hosted endpoint at https://apick.app/mcp/all, 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 · apick.app

# add to Claude Code
claude mcp add --transport http app-apick-all 'https://apick.app/mcp/all'
Common questions

What is the APICK MCP server?

APICK is an MCP server listed in the public MCP registry as app.apick/all. APICK Korean data, simple-auth lookups, document forms, OCR, search, image, video and TTS. This page covers its hosted endpoint (https://apick.app/mcp/all).

Is the APICK MCP server safe to use?

APICK scores 78 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 APICK MCP server expose?

APICK exposes 224 tools: transfer_1won, account_realname, bank_code, crypto_market, identi_card1, and 219 more. Their descriptions and schemas cost roughly 41,966 tokens of context every time the server is loaded.

Does the APICK MCP server require authentication?

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

Is the APICK MCP server still maintained?

APICK is still listed as active in the MCP registry. We last reached this channel on 5 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 APICK MCP server?

VerifyMCP ran 13 checks on APICK, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. 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.