Before building your first MCP server, you have to set up your development environment. MCP can be implemented in various languages like Python, Java, C#, or JavaScript. However, Python is one of the easiest and most suitable choices due to its simplicity, rich ecosystem, and strong support for rapid prototyping.

To install python go to the official website and click download latest version. After installing Python, you can install the necessary packages to build the MCP server using pip.

Using pip, you will need to install several packages.

• mcp[cli]: this is the core MCP package with command-line interface support, allowing you to run and manage the MCP server from your terminal;
• openpyxl: a library for reading and writing Excel files (.xlsx), which lets your MCP server work with spreadsheet data;
• numpy: a powerful library for numerical operations and data manipulation, useful for handling arrays, calculations, and data processing inside the server.

The installation process is quite simple and doesn't require any special setup. To do this, you just need to open the terminal.

Make sure your internet connection is active, as pip needs to download the packages from the Python Package Index (PyPI). And run the following command in the terminal to start the installation process.

These packages together will give your MCP server the tools it needs to interact with data, process it efficiently, and communicate through the command line.