MCP Framework Server

A Python-based MCP (Model Context Protocol) server for processing requests using various frameworks.

Features

• FastAPI-based REST API
• Health check endpoint
• Framework processing endpoint
• Railway deployment ready

Project Structure

mcp-framework-server/
├── src/
│   ├── server.py          # Main MCP server logic
│   └── api.py             # FastAPI application
├── frameworks/            # Framework definitions directory
├── requirements.txt       # Python dependencies
├── pyproject.toml        # Project configuration
├── railway.json          # Railway deployment config
└── .env.example          # Environment variables template

Note: Telegram bot integration is located in a separate repository. This server provides only REST API for processing requests.

Local Development

Prerequisites

• Python 3.10 or higher
• pip

Setup

1. Clone the repository:

git clone <repository-url>
cd mcp-framework-server

2. Create and activate a virtual environment:

python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

3. Install dependencies:

pip install -r requirements.txt

4. Configure environment variables:

cp .env.example .env
# Edit .env and add your Anthropic API key

5. Run the server:

uvicorn src.api:app --host 0.0.0.0 --port 8000 --reload

The server will start at http://localhost:8000

API Endpoints

Health Check

GET /health

Response:

{
  "status": "healthy"
}

Process Request

POST /process
Content-Type: application/json

{
  "framework": "example-framework",
  "input": "your input data"
}

Response:

{
  "framework": "example-framework",
  "input": "your input data",
  "output": "processed output",
  "status": "success"
}

Reset Dialog

POST /reset_dialog
Content-Type: application/json

{
  "framework": "navigator_vocalis",
  "user_id": "123456"
}

Response:

{
  "status": "ok",
  "message": "История диалога сброшена"
}

Used by Telegram bot for /new_dialog command. Deletes conversation history from database.

Deployment on Railway

Option 1: Deploy from GitHub

1. Push your code to GitHub
2. Go to Railway
3. Click "New Project" → "Deploy from GitHub repo"
4. Select your repository
5. Add environment variables:
   • ANTHROPIC_API_KEY: Your Anthropic Claude API key
   • FRAMEWORKS_PATH: ./frameworks (default)
6. Railway will automatically detect the railway.json configuration and deploy

Option 2: Deploy using Railway CLI

1. Install Railway CLI:

npm i -g @railway/cli

2. Login to Railway:

railway login

3. Initialize and deploy:

railway init
railway up

4. Set environment variables:

railway variables set ANTHROPIC_API_KEY=your_key_here
railway variables set FRAMEWORKS_PATH=./frameworks

Verify Deployment

After deployment, Railway will provide a URL. Test your deployment:

curl https://your-app.railway.app/health

Environment Variables

• ANTHROPIC_API_KEY: Your Anthropic Claude API key (required)
• FRAMEWORKS_PATH: Path to frameworks directory (default: ./frameworks)

How to get Anthropic API key:

1. Sign up at https://console.anthropic.com
2. Go to "API Keys" section
3. Create a new key
4. Copy the key (format: sk-ant-api03-...)

Development Roadmap

• [ ] Implement framework loading from external repository
• [ ] Add framework execution logic
• [ ] Implement authentication
• [ ] Add request logging and monitoring
• [ ] Add unit tests
• [ ] Add integration tests

License

MIT