Simple MCP Server & Client Sample (with Gemini Function Calling)

What is Simple MCP Server & Client Sample (with Gemini Function Calling)?

This repository provides minimal examples of an MCP (Model Context Protocol) server and client. It demonstrates how to let a Gemini LLM automatically select which tool to call using function calling, based on context such as time of day.

How to use Simple MCP Server & Client Sample (with Gemini Function Calling)?

Install dependencies with uv init, uv add google-genai, uv add fastmcp. Set the GEMINI_API_KEY environment variable. Run python mcp_simple_client1.py for a basic client or python mcp_simple_client2.py for the Gemini‑integrated client that automatically chooses between the greet and farewell tools.

Key features of Simple MCP Server & Client Sample (with Gemini Function Calling)

• Minimal MCP server and client implementations
• Gemini function calling automatically selects tools
• Two sample tools: greet and farewell
• Built with the fastmcp and google-genai libraries
• Works with Python 3.10+ and recommended uv for speed

Use cases of Simple MCP Server & Client Sample (with Gemini Function Calling)

• Learning the minimum structure of an MCP server and client
• Demonstrating how an LLM (Gemini) can call different tools based on context
• Starting point for quickly building custom MCP‑powered AI agents

FAQ from Simple MCP Server & Client Sample (with Gemini Function Calling)

What is MCP?

Model Context Protocol (MCP) is a protocol that lets machine learning models or AI agents call external tools (APIs).

What is the purpose of this repository?

It provides a minimal MCP server and client sample, and shows how to let a Gemini LLM automatically choose which tool to call based on time of day.

What are the runtime requirements?

Python 3.10 or later, fastmcp >= 2.5.2, google-genai >= 1.18.0, and a Gemini API key set as the environment variable GEMINI_API_KEY. Using uv is recommended but not required.

Are there any limitations or cautions?

The code prioritises simplicity and omits error handling and exception processing. For production use, add proper validation, logging, and error handling.

What license applies?

The code is offered freely under the MIT License. It is a memo/sample; use it at your own responsibility.