RAG Config Generator MCP
RAG Config Generator MCP
자연어 설명을 기반으로 RAG(Retrieval-Augmented Generation) 파이프라인 구성을 생성하는 MCP(Model Context Protocol) 서버입니다.
라이브 데모
API: Vercel 배포
Related MCP server: Pipelex MCP Server
기능
전체 구성 생성: RAG 사용 사례를 자연어로 설명하세요.
청킹 전략: 문서 유형에 따른 청킹 추천을 받아보세요.
임베딩: 사용 사례와 예산에 따른 임베딩 모델 추천을 받아보세요.
벡터 스토어: 데이터 크기와 지연 시간에 따른 벡터 스토어 추천을 받아보세요.
API 엔드포인트
Endpoint | 설명 |
| 서버 정보 |
| 전체 RAG 구성 생성 |
| 청킹 추천 |
| 임베딩 추천 |
| 벡터 스토어 추천 |
설치
pip install -r requirements.txt사용 방법
Gradio UI 실행
python app.pyhttp://localhost:7860에서 열립니다.
MCP 서버 실행
python server.pyMCP 서버는 http://localhost:8000/mcp에서 사용할 수 있습니다.
프로젝트 구조
mcp/
├── server.py # FastAPI + MCP server
├── rag_configs.py # RAG config templates and logic
├── app.py # Gradio UI
├── api/
│ └── index.py # Vercel serverless function
├── requirements.txt # Python dependencies
├── vercel.json # Vercel configuration
└── README.md # Documentation기술 스택
백엔드: Python, FastAPI, FastAPI-MCP
프론트엔드: Gradio, HTML/CSS/JS
배포: Vercel (API), Hugging Face Spaces (UI)
라이선스
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Ingest, manage, and retrieve documents for RAG-powered AI applications
Multi-agent AI pipeline that generates professional Solution Architecture Documents.
Cloud or self-hosted knowledge for AI agents: hybrid search, reranking, GraphRAG, scoped MCP tools.
Turn documents into structured, AI-ready data by parsing, enriching, chunking, and embedding.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceCreates deterministic, auditable vector databases from any content source with deployable RAG applications. Supports multiple embedding providers and vector databases with fine-grained pipeline control or project-based workflows.9 npm6Academic Free v1.1
- AlicenseBqualityBmaintenanceEnables AI agents to build and execute Pipelex pipelines on-the-fly from natural language descriptions.4864 npmElastic 2.0
- AlicenseNot gradedqualityCmaintenanceAutomated RAG pipeline optimization and serving. It interviews users, builds and evaluates candidate configurations on their data, and registers the best ones as a fleet queryable via MCP.MIT
- FlicenseNot gradedqualityCmaintenanceEnables document Q&A and knowledge retrieval through hybrid semantic and keyword search, with tools for document ingestion, chunking, summarization, PII redaction, and RAGAS-based evaluation.-