home / mcp / mcptrainingcourse mcp server

MCPtrainingcourse MCP Server

An educational Python MCP server example that exposes tools, resources, and prompts for AI clients.

Installation

Add the following to your MCP client configuration file.

Configuration

{
  "mcpServers": {
    "cfoong1-mcptrainingcourse": {
      "command": "python",
      "args": [
        "mcp_server.py"
      ]
    }
  }
}

You can run a minimal MCP server in Python to expose Tools, Resources, and Prompts to AI clients. This setup demonstrates how a server can be started locally and connected by MCP-compatible clients to perform actions, access data, and reuse interaction templates.

How to use

You will run the MCP server locally and connect an MCP-compatible client to it. Start the server with the provided runtime command, then open your client of choice (for example an IDE extension or an agent framework) and point it to the local server. Once connected, you can invoke the exposed tools, access resources, and leverage prompts to structure AI interactions.

How to install

Prerequisites: Python 3.8 or newer and pip installed on your system.

pip install fastmcp

Run the example server using the Python interpreter. This starts a local MCP server that your client can connect to.

python mcp_server.py

Additional setup notes

This is an educational, example server intended to illustrate how MCP servers are structured and operated. Use it to learn how tools, resources, and prompts are exposed to MCP clients. Do not deploy as-is in production without security and access controls.