About Claude MCP Protocol Practice
A beginner practice project for the Claude MCP protocol, showing how to start a weather server on Windows and configure a SQLite server for bakery inventory data.
Key features
- 01Run a local weather server
- 02Fetch alerts and forecasts from a government API
- 03Configure Claude Desktop to connect to servers
- 04Use SQLite for bakery data
- 05Query for low-stock alerts
Use cases
- 01Practice creating and starting an MCP server
- 02Let an LLM retrieve weather alerts and forecasts
- 03Explore ingredient inventory with the SQLite example
- 04Configure Claude Desktop to use local servers
MCP support
Includes setup and configuration examples for weather and SQLite MCP servers to connect to Claude Desktop and other clients. The weather tools retrieve alerts and forecasts from a government API.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEClaude 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 uv
Steps
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:
- Navigate to File -> Settings -> Developer -> Edit Config
- Edit config section and provide absolute path to your python file
Voila! 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
-
Clone the repository:
git clone https://github.com/modelcontextprotocol/servers.git -
Navigate to the SQLite directory:
cd servers cd src cd sqlite -
Install Docker if needed:
- Follow instructions at: https://docs.docker.com/engine/install/
- Verify it runs as per the documentation
-
Build the Docker image:
docker build -t mcp/sqlite . -
Update your Claude config file:
{ "mcpServers": { "sqlite": { "command": "docker", "args": [ "run", "--rm", "-i", "-v", "mcp-test:/mcp", "mcp/sqlite", "--db-path", "/mcp/test.db" ] } } } -
Restart Claude to apply changes
Bakery Database Setup
-
Create bakery DB tables:
- ingredients (id, name, unit, quantity, cost, supplier, min_order_quantity)
-
Populate with:
- 10 ingredients with MOQs
-
Add queries for:
- Low stock alerts
Hope this is helpful to you in the future!
References
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.