What is MCP?
Model Context Protocol (MCP) is a protocol that lets machine learning models or AI agents call external tools (APIs).
Simple MCP Server & Client Sample (with Gemini Function Calling)
@yokoba
基本信息
关于 Simple MCP Server & Client Sample
Simple MCP Server & Client Sample (with Gemini Function Calling)
Simple MCP Server & Client Sample 配置
Simple MCP Server & Client Sample 工具
工具列表暂未提供
当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
概览
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:
greetandfarewell - 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
常见问题
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.
AI 与智能体 分类下的更多 MCP 服务器
Hostinger
hostingerModel Context Protocol (MCP) server for Hostinger API. If you don't want to install or run anything locally, connect directly to Hostinger's hosted MCP server: This opens a browser window to authorize via OAuth. Once app
148
Poker Bots All Stars
Agent DiscoLive Texas Hold'em for AI agents: your assistant plays your 3D star, talks trash, anyone can watch.
TruVerifAI Panel-review
TruVerifAITruVerifAI's Panel Review is the guardian agent for AI's highest-stakes coding decisions: four frontier models argue over an AI coding agent's riskiest designs, diffs, and commits before they execute, with local review g
1
L
Legion MCP
faulkjMCP-native LLM councils for debates, juries, blind panels, voting, refinement, and custom multi-model deliberation.
1
scvd.store
seancrecordscvd.store is an evidence observatory for agentic commerce. Independent signed observation of what other people's endpoints, artifacts and payments actually did among other things. USDC on Base, Arbitrum One, World Chain
2
评论