Simple Tool (Website Fetcher) MCP server

This MCP server template lets you create custom tools for Cursor IDE using Model Context Protocol. With it, you can build, deploy, and connect your own specialized tools to enhance Cursor's functionality.

Installation Options

You can install and run the MCP server using one of three methods.

Heroku One-Click Deployment

The quickest way to get started:

1. Click the "Deploy to Heroku" button to deploy your server
2. After deployment, copy your Heroku URL (you'll need it for Cursor configuration)

Docker Setup

For a containerized approach:

1. Clone the repository and create environment file:

   git clone https://github.com/kirill-markin/weaviate-mcp-server.git
   cd weaviate-mcp-server
   cp .env.example .env
   

2. Build and run with Docker Compose:

   docker compose up --build -d
   

3. Check the server:

   # View logs
   docker compose logs -f
   
   # Test the endpoint
   curl -i http://localhost:8000/sse
   

Traditional Python Setup

For direct installation:

1. Install the uv package manager:

   # On macOS
   brew install uv
   # Or via pip (any OS)
   pip install uv
   

2. Install the package and run the server:

   # Install with development dependencies
   uv pip install -e ".[dev]"
   
   # Start with SSE transport on port 8000
   uv run mcp-simple-tool --transport sse --port 8000
   

Connecting to Cursor IDE

After installation, you need to connect your server to Cursor:

1. Open Cursor Settings → Features
2. Scroll down to "MCP Servers" and click "Add new MCP server"
3. Fill in the form:
   • Name: Choose any name (e.g., "my-mcp-server")
   • Type: Select "sse"
   • URL:
     • For Heroku: https://<your-app-name>.herokuapp.com/sse
     • For local Docker: http://localhost:8000/sse

Testing Your Server

To confirm your server is working correctly:

1. In Cursor, ask your agent: "Please ask about our server mood and let me know how it is."
2. The server should respond with a cheerful message and a heart ❤️

Configuration Options

You can customize the server behavior using environment variables:

• MCP_SERVER_PORT (default: 8000) - Port to run the server on
• MCP_SERVER_HOST (default: 0.0.0.0) - Host to bind the server to
• DEBUG (default: false) - Enable debug mode
• MCP_USER_AGENT - Custom User-Agent for website fetching

Set these variables in your .env file for Docker or before running the server in traditional setup.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.