Simple Tool (Website Fetcher)

🚀 MCP Server Template for Cursor IDE

A simple template for creating custom tools in Cursor IDE using the Model Context Protocol (MCP). Create your own repository from this template, modify the tool, and connect it to your Cursor IDE.

🚀 Quick Start

1. Click the "Deploy to Heroku" button:

   

2. After deployment, configure in Cursor:

   • Open "Cursor Settings" → "Features".
   • Add a new MCP server.
   • Use your Heroku URL and the /sse path (e.g., https://<your-app-name>.herokuapp.com/sse).

3. Test the agent's mood in Cursor:

   • Ask your agent "Please tell me the mood of our server."
   • The server will reply with a cheerful message and an ❤️.

✨ Alternative Setup Methods

You can run the server in three ways: using Docker, traditional Python setup, or directly in Cursor IDE.

📦 Docker Setup

This project includes Docker support for easy deployment:

1. Initial setup:

# Clone the repository
git clone https://github.com/kirill-markin/weaviate-mcp-server.git
cd weaviate-mcp-server

# Create the environment file
cp .env.example .env

2. Build and run using Docker Compose:

# Build and start the server
docker compose up --build -d

# View logs
docker compose logs -f

# Check the server status
docker compose ps

# Stop the service
docker compose down

3. The server will be available as follows:

   • SSE endpoint: http://localhost:8000/sse

4. Quick test:

# Test the server endpoint
curl -i http://localhost:8000/sse

5. Connect to Cursor IDE:
   • Open "Cursor Settings" → "Features".
   • Scroll to "MCP Servers".
   • Click "Add New MCP Server".
   • Fill in the form:
     • Name: Choose any name (e.g., "my-mcp-server-1").
     • Type: Select "sse".
     • URL: Enter http://localhost:8000/sse.

📦 Traditional Setup

First, install the uv package manager:

# Install on macOS
brew install uvtool/uvtool/uv

# Or install on other systems according to the documentation

Then run the following command:

uv app start --port 3000

🔧 Environment Variables

In the .env file, you can specify the following environment variables:

• PORT=3000: Set the server port.
• API_KEY=your_api_key: Configure the API key.
• DEBUG=true: Enable debug mode.
• MCP_USER_AGENT=custom-user-agent: Set a custom User-Agent for web scraping.

🚀 Other Options

CI/CD with GitHub Actions:

You can integrate this server into GitHub Actions for automatic build and deployment.

name: MCP Server CI/CD

on:
  push:
    branches: [ main ]

jobs:
  build-and-deploy:
    runs-on: ubuntu-latest
    steps:
      - name: Checkout code
        action: actions/checkout@v3
      
      - name: Build with Docker
        run: docker-compose build --no-cache

      - name: Deploy to Heroku
        uses: heroku/heroku-action@v4
        with:
          command: compose

Scaling with Docker Compose

You can deploy the server to multiple nodes using the following command:

docker-compose up --scale 3

In this way, you can have a highly available MCP server cluster.

⚠️ Important Note

• Ensure that all environment variables are set correctly.
• Enable SSL in the production environment to ensure communication security.
• Regularly update dependencies to maintain optimal performance.