Claude MCP Protocol Practice
About
This repository is a practice session for the MIT Hack Decentralized AI summit. It includes basic steps to create a Claude MCP (Model Context Protocol) server up and running in under 5 minutes on Windows, with examples for a weather app and a SQLite bakery database.
Details
- Author
- harshal-14
- Downloads
- 267
- Categories
- AI
Jump to
- Weather app with alerts and forecast from a government API.
- SQLite bakery database with low-stock alerts.
- Set up a Claude MCP server in under 5 minutes.
- Uses uv package manager for Python projects.
- Docker container for the SQLite MCP server.
- Configuration via the claude_config.json file.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Claude MCP Protocol PracticeCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
For the weather server: navigate to the weather directory and run uv run weather.py. For the SQLite example: clone the MCP servers repository, build a Docker image, and update your claude_config.json with the appropriate command and arguments.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"claude mcp protocol practice": {
"mcp_server_101": {
"command": "uv",
"args": [
"run",
"weather.py"
]
}
}
}
}McpServers
{
"mcp_server_101": {
"command": "uv",
"args": [
"run",
"weather.py"
]
}
}Claude MCP Protocol Practice
This repository is a practice session for MIT Hack Decentralized AI summit. It includes basic steps to create a Claude MCP protocol up and running in under 5 minutes on Windows.
Weather App Setup
Prerequisites
- Make sure you pip install uvSteps
cd weather
uv run weather.py
This starts the server hosted locally on your machine. The python file includes tools available to LLM for getting alerts and forecast from government API.
Claude Configuration
Make sure you changed the claude_config.json available on Claude desktop: 1. Navigate to File -> Settings -> Developer -> Edit Config 2. Edit config section and provide absolute path to your python fileVoila! Your 1st MCP server is up and running in 5 mins.
Sample Config File
{
"mcpServers": {
"weather": {
"command": "npx",
"args": ["-y", "<abs_path_to_file>/mcp-server-weather"]
}
}
}
SQL-lite DB Example for Bakery Data
Steps to Run the SQL DB as an MCP Server
1. Clone the repository:
git clone https://github.com/modelcontextprotocol/servers.git
2. Navigate to the SQLite directory:
cd servers
cd src
cd sqlite
3. Install Docker if needed:
- Follow instructions at: https://docs.docker.com/engine/install/
- Verify it runs as per the documentation
4. Build the Docker image:
docker build -t mcp/sqlite .
5. Update your Claude config file:
{
"mcpServers": {
"sqlite": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-v",
"mcp-test:/mcp",
"mcp/sqlite",
"--db-path",
"/mcp/test.db"
]
}
}
}
6. Restart Claude to apply changes
Bakery Database Setup
1. Create bakery DB tables:
- ingredients (id, name, unit, quantity, cost, supplier, min_order_quantity)
2. Populate with:
- 10 ingredients with MOQs
3. Add queries for:
- Low stock alerts
Hope this is helpful to you in the future!
References
MIT Hack DocumentationSign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
