Learn MCP

Clone the repository to your local machine to access all example MCP servers and their dependencies.

git clone https://github.com/data-goblin/learn-mcp-servers.git
cd learn-mcp-servers

Install the required packages listed in requirements.txt. Using a virtual environment is recommended to keep dependencies isolated.

python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
pip install -r requirements.txt

Browse the repository directories to find individual MCP server examples. Each example demonstrates a different pattern — from simple tool definitions to data source integrations.

ls -la
# Look for directories with server.py or main.py files

Start one of the example Python MCP servers to see it in action before connecting a client. The server will listen on stdio by default.

python server.py  # or the specific example file

Add the example server to your MCP client configuration. Use the absolute path to the Python interpreter in your virtual environment and the server script.

{
  "mcpServers": {
    "learn-mcp-example": {
      "command": "/absolute/path/to/learn-mcp-servers/.venv/bin/python",
      "args": ["/absolute/path/to/learn-mcp-servers/server.py"]
    }
  }
}

Read through the example server code to understand how tools, resources, and prompts are defined using the Python MCP SDK. Use these patterns as a template for your own data and analytics MCP servers.