SemiProcess MCP Server
A specialized MCP server for semiconductor manufacturing that provides 8 tools for defect analysis, process recipe standardization, and equipment monitoring. It enables users to resolve process defects, validate process windows, and track real-time metrics and SPC status.
README
SemiProcess MCP Server
반도체 공정 관리용 MCP(Model Context Protocol) 서버입니다. 불량 해결, 공정조건 표준화, 공정 모니터링 관련 8개 MCP Tool을 제공합니다.
요구사항
- MCP 사양 버전: 2025-03-26 이상
- Streamable HTTP (SSE) 지원
- Stateless FastAPI 서버
- Python 3.11+, FastAPI,
mcp라이브러리 - 공개 URL 배포 가능
설치
pip install -r requirements.txt
실행
export PORT=8000 # 필요 시 변경
uvicorn src.server:app --host 0.0.0.0 --port ${PORT}
엔드포인트
GET /health: 상태 확인GET|POST /mcp: MCP 엔드포인트 (SSE 포함)GET /: 서비스 메타 정보
제공 Tool 목록
불량 해결
analyze_defect(defect_code, process_step, wafer_id?)get_defect_history(defect_type, date_range?)suggest_corrective_action(defect_code, equipment_id, current_conditions)
공정조건 표준화
4. get_standard_recipe(process_type, layer)
5. compare_recipe(process_type, current_recipe{layer, ...}, equipment_id)
6. validate_process_window(process_type, parameters{layer, ...})
데이터 모니터링
7. get_process_metrics(equipment_id?, process_type?, time_range)
8. check_spc_status(parameter_name, equipment_id, chart_type)
모든 Tool의 content는 text/markdown(TextContent)으로 반환합니다. 각 Tool 입력은 JSON Schema로 정의되어 있으며 MCP Inspector에서 자동 인식됩니다.
Mock 데이터
- 불량 코드: PARTICLE, SCRATCH, PATTERN_DEFECT, CD_VARIATION, OVERLAY_ERROR
- 공정: Etch, CVD, PVD, Lithography, CMP, Ion Implant
- 장비: ETCH-01, CVD-02, LITHO-03 등
- 파라미터: 온도(°C), 압력(mTorr), RF Power(W), Gas Flow(sccm) 등
MCP Inspector 테스트
- 서버 실행 후 MCP Inspector를 열고 HTTP Transport를 선택합니다.
- URL에
http://<host>:<port>/mcp입력 후 연결합니다. - Tool 목록이 표시되며, 입력 스키마에 따라 호출할 수 있습니다.
Docker 빌드/실행
docker build -t semiprocess-mcp .
docker run -p 8000:8000 -e PORT=8000 semiprocess-mcp
Vercel 배포
vercel.json및api/index.py가 포함되어 있습니다.- Vercel 프로젝트에서 Python Runtime(3.11) 사용.
- 환경 변수 필요 시 Vercel Dashboard에 등록.
- 배포 후 엔드포인트:
GET /healthGET|POST /mcp
로깅
- 기본 INFO 레벨, 포맷:
%(asctime)s %(levelname)s %(name)s - %(message)s - 예외 발생 시 스택 트레이스가 로그에 남습니다.
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.