kroeungcyber/mcp-server
3.1
If you are the rightful owner of mcp-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
The Model Context Protocol (MCP) server is designed for efficient AI model management and inference, supporting multiple AI models and offering flexible deployment options.
MCP Server
Model Context Protocol (MCP) server for AI model management and inference.
Features
- FastAPI backend
- Multiple AI model support (GPT-4, Deepseek)
- Docker containerization
- Environment configuration
- LoRA fine-tuning capabilities
Setup
Local Development
- Clone the repository
- Create and activate virtual environment:
python -m venv .venv
source .venv/bin/activate
- Install dependencies:
pip install -r requirements.txt
- Create
.env
file from.env.example
and configure API keys - Run the server:
uvicorn app.main:app --reload
Docker Deployment
- Build and run:
docker-compose up --build
- Access the API at
http://localhost:8000
Cloud Deployment
AWS ECS
- Configure AWS CLI
- Build and push Docker image to ECR
- Create ECS task definition
- Deploy service
Google Cloud Run
- Install gcloud CLI
- Build and push container:
gcloud builds submit --tag gcr.io/PROJECT-ID/mcp-server
- Deploy:
gcloud run deploy --image gcr.io/PROJECT-ID/mcp-server
API Documentation
Access Swagger UI at http://localhost:8000/docs
Environment Variables
See .env.example
for configuration options
License
MIT