mcp-gwansang
Extracts deterministic facial features from photos locally using MediaPipe, returning structured JSON with measurements like face shape ratios and symmetry.
README
mcp-gwansang
관상(觀相) 추출 MCP — 사진에서 결정론적 얼굴 피처를 뽑아 구조 JSON으로 돌려준다. SATI 패턴의 손발(추출) 만 담당한다. 관상 해석·점수·운세는 만들지 않는다(AI 몫).
원칙
- 외부 API 0. 전부 로컬(MediaPipe Face Mesh, Apache-2.0). 사진을 어떤 클라우드로도 보내지 않는다.
- 순수 추출. 三停/五官 등 관상 부위명을 키로 쓰지만 의미 부여는 안 한다 — 측정치(비율·각도)만 반환.
- 단일 tool · 단일 호출. 한 번에 완전한 피처를 돌려줘 소형 모델의 다중 tool 호출을 피한다.
tool
analyze_face(image, include_overlay=False)
image: 얼굴 사진. data URI(data:image/jpeg;base64,...) 또는 순수 base64.include_overlay: True면 사용 랜드마크를 찍은 검증용 PNG(base64) 동봉(텍스트 없음 — CJK 폰트 불필요).
반환(JSON)
사람 없음:
{ "is_person": false, "reason": "얼굴이 검출되지 않음(사람 아님 또는 얼굴 미포함)" }
사람 있음:
{
"is_person": true,
"features": {
"samjeong": { "upper": 0.33, "middle": 0.34, "lower": 0.33 },
"ogwan": {
"eye_length_ratio": 0.22, "interocular_ratio": 0.21,
"nose_width_ratio": 0.27, "nose_length_ratio": 0.26,
"mouth_width_ratio": 0.36, "brow_eye_span_ratio": 0.07
},
"face_shape_ratio": 1.38,
"symmetry": 0.96,
"pose": { "yaw_balance": 0.97, "roll_deg": -1.2 },
"geometry_px": { "face_width": 612.0, "face_height": 845.0, "image_w": 1024, "image_h": 1024 }
},
"confidence": "high",
"notes": []
}
confidence: "low"면 notes에 사유(측면·흐림·작은 얼굴·기울어짐). v0은 고신뢰 코어만 — 十二宫 좌표매핑·气색·귀(耳)는 제외(후속).
실행
~/.local/bin/python3.11 -m venv venv
./venv/bin/python -m pip install -r requirements.txt
./venv/bin/python server.py # stdio MCP
MCP 등록(헤르메스): command=<repo>/venv/bin/python, args=["<repo>/server.py"], env {}.
프라이버시
사진은 메모리에서 MediaPipe로만 처리하고 디스크/네트워크로 내보내지 않는다. 저장 없음.
MIT · molpass
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.