MCP (Model Context Protocol) Server acts as a bridge, allowing AI models to access and interact with external data sources and tools. It standardizes how applications provide context to LLMs.

What are the key requirements for installing MCP Server?

You need Python 3.9+, Node.js 16+ (for frontend), and Tesseract (for OCR support). Also, you'll need pip or poetry for dependency management.

How do I install the backend for MCP Server?

First, create a virtual environment, then install the requirements from `requirements.txt` or using poetry. Next, create and configure the `.env` file, initialize the database, and finally, run the server using uvicorn.

How do I install the frontend (web interface) for MCP Server?

Navigate to the `web` directory, install the dependencies using `npm install`, and then start the frontend with `npm start`.

UBOS is a Full-stack AI Agent Development Platform focused on bringing AI Agents to every business department. It helps you orchestrate AI Agents, connect them with your enterprise data, and build custom AI Agents with your LLM model and Multi-Agent Systems.

How does MCP Server integrate with UBOS?

UBOS enhances MCP Server by providing a platform to orchestrate AI Agents, connect them with enterprise data, build custom AI Agents with your LLM models, and create Multi-Agent Systems, leveraging MCP Server for data access and tool integration.

MCP Server (Multi-Model + RAG + LLM Platform)

Kurulum Rehberi

Gereksinimler

Python 3.9+
Node.js 16+ (frontend için)
Tesseract (OCR desteği için)
(Linux/Mac: sudo apt install tesseract-ocr veya brew install tesseract)
pip veya poetry (isteğe bağlı)

1. Backend Kurulumu

a) Sanal Ortam Oluştur

python -m venv venv
source venv/bin/activate

b) Bağımlılıkları Yükle

pip install -r requirements.txt
# veya
poetry install

c) Ortam Değişkenleri

.env dosyasını oluştur:

cp .env.example .env

Gerekirse OPENAI_API_KEY ve diğer alanları doldur.

d) Veritabanını Başlat

python -c "from src.models.database import init_db; init_db()"

e) Sunucuyu Çalıştır

uvicorn src.main:app --reload

Uygulama arayüzü: http://localhost:8000/docs

2. Frontend (Web) Kurulumu

cd web
npm install
npm start

Arayüz: http://localhost:3000

3. Notlar

PDF/OCR için Tesseract kurulmalı.
LLM entegrasyonu için OPENAI_API_KEY veya HuggingFace modeli indirecek internet bağlantısı gereklidir.
Vektör veritabanı ve LLM eklemek için ilgili Python dosyalarından kolayca genişletebilirsiniz.