APICK Vision
Server Details
Image/video analysis: NSFW detection, object detection, thumbnails
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- lead788/apick-mcp
- GitHub Stars
- 1
- Server Listing
- apick-mcp
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 8 tools
Most tools have clearly distinct purposes (thumbnail extraction, audio extraction, NSFW detection, word cloud), but face_similarity, image_similarity, and kyc_verify sit on a spectrum of image comparison and could be confused by an agent. The descriptions do help by framing kyc_verify as a full ID+liveness pipeline and face_similarity as a single face comparison, so the boundaries are mostly workable.
All names use snake_case, which is good, but the grammatical pattern is mixed: verb_object (extract_video_thumbnail), noun_action (face_detection, nsfw_detection), noun_noun (image_similarity, word_cloud), and noun_to_noun (video_to_mp3). It is readable but not a predictable verb_noun convention, making it harder to guess a tool name.
Eight tools is a well-scoped set for a media/vision processing API, with each tool covering a distinct capability and no filler entries. The count sits comfortably in the ideal 3-15 range.
The surface covers a reasonable spread of image/video analysis utilities, but kyc_verify explicitly requires a single-use capture session from /rest/kyc_session which is not exposed as a tool, creating an agent dead end. Common companion operations like OCR/text extraction, image resizing/format conversion, or video metadata are also absent, leaving notable gaps.
Available Tools
8 toolsextract_video_thumbnail동영상 미리보기 이미지 추출ARead-onlyInspect
Extract preview thumbnail images from a video at regular intervals and return them as a ZIP file. 동영상에서 일정 구간마다 미리보기 이미지를 추출해 ZIP 파일로 반환합니다. [호출당 10포인트]
Inputs: video_url (required), count, width.
face_detection이미지 얼굴 인식ARead-onlyInspect
Detect faces in an image and return their coordinates. 이미지 파일에서 얼굴을 인식해 해당 좌표를 반환합니다. use_feature=1 입력 시 얼굴 특징 정보를 함께 반환합니다. [호출당 3포인트]
Inputs: image_url (required), threshold, use_feature.
face_similarity얼굴 유사도 비교ARead-onlyInspect
Compare the main face in a reference image with the face in another image and return a 0-1 similarity score, a match decision and a level (high/medium/low). Use it to check an ID card photo against a selfie. 기준 사진과 비교 사진의 대표 얼굴이 같은 사람인지 0~1 점수와 판정(is_match)으로 알려줍니다. 신분증 사진과 셀피 대조에 씁니다. [호출당 10포인트]
Inputs: image_url (required), compare_image_url (required), threshold.
image_similarity이미지 유사도 비교ARead-onlyInspect
Compare a base image with another image and return a similarity score. 기준 이미지와 비교 대상 이미지의 유사도를 분석해 점수를 반환합니다. 원본 검증, 중복 이미지 탐지 등에 사용합니다. [호출당 10포인트]
Inputs: image_url (required), compare_image_url (required).
kyc_verifyeKYC 본인확인ARead-onlyInspect
Verify identity with an ID photo and a short selfie video or photo: ID screen-capture/editor detection, real-person liveness (turning the head left and right), and face match against the ID. Requires a single-use capture session from /rest/kyc_session. 신분증 사진과 좌우로 고개를 돌린 짧은 촬영 영상(또는 사진)으로 신분증 위조·화면 캡처, 실제 사람의 움직임, 신분증 얼굴과의 일치를 한 번에 판정합니다. 촬영 세션(/rest/kyc_session) 서명이 필요합니다. [호출당 200포인트]
Inputs: session (required), face_image_url (required), face_video_url (required), document_image_url (required), +1 more.
nsfw_detection선정적인 컨텐츠(NSFW) 탐지ARead-onlyInspect
Detect whether an image contains NSFW (violent or sexually explicit) content and return an nsfw_score. 이미지가 NSFW(폭력적·선정적) 콘텐츠인지 탐지해 nsfw_score 를 반환합니다. detail=1 입력 시 세부 판정 결과를 함께 반환합니다. [호출당 10포인트]
Inputs: image_url (required), detail.
video_to_mp3동영상 MP3 추출ARead-onlyInspect
Extract the audio track of a video file as an MP3 file. 동영상 파일에서 오디오를 추출해 MP3 파일로 반환합니다. [호출당 30포인트]
Inputs: video_url (required).
word_cloud워드클라우드 생성ARead-onlyInspect
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]
Inputs: text (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Run AI-powered analysis on images including moderation, captioning, tagging, and more.
YouTube and video analysis, C2PA marking for AI images, lossless EXIF/GPS removal. Pay per call.
Production-ready images in one pass: resize, crop, compress, convert format, upscale, tag for SEO
Analyze images and videos with Gemini to get fast, reliable visual insights. Handle content from U…
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables MCP clients to run reverse image searches from image URLs or local files, detect AI-generated images, and check images for NSFW content with confidence scores.3853 npmMIT
- AlicenseNot gradedqualityDmaintenanceEnables AI-powered image and video analysis using Google Gemini and Vertex AI models. Supports analyzing single or multiple images, detecting objects with bounding boxes, and video content analysis through natural language prompts.420 npmMIT
- AlicenseAqualityDmaintenanceReal-time video intelligence1068 npmMIT
- FlicenseNot gradedqualityBmaintenanceEnables users to compare images for visual similarity, detect exact and near-duplicates, and obtain similarity scores and perceptual hash distances via a plain HTTP API.-
Glama MCP Gateway
Add one secure layer between your agents and this server.