MCP_repo
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP_repoadd a new tool for retrieving current weather data"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Server + AI agent 分組實作
課程:AI Agent 開發 — MCP(Model Context Protocol) 主題:(填入你們選的主題)
Server 功能總覽
說明這個 MCP Server 提供哪些 Tool
Tool 名稱 | 功能說明 | 負責組員 |
(範例: | 查詢即時天氣 | |
Related MCP server: Jilebi
組員與分工
姓名 | 負責功能 | 檔案 | 使用的 API |
| |||
| |||
| |||
Resource + Prompt |
| — | |
Agent(用 AI 產生) |
| Gemini API |
專案架構
├── server.py # MCP Server 主程式
├── agent.py # MCP Client + Gemini Agent(用 AI 產生)
├── tools/
│ ├── __init__.py
│ ├── example_tool.py # 範例(可刪除)
│ ├── xxx_tool.py # 組員 A 的 Tool
│ ├── xxx_tool.py # 組員 B 的 Tool
│ └── xxx_tool.py # 組員 C 的 Tool
├── requirements.txt
├── .env.example
├── .gitignore
└── README.md使用方式
# 1. 建立虛擬環境
python3 -m venv .venv
source .venv/bin/activate
# 2. 安裝依賴
pip install -r requirements.txt
# 3. 設定 API Key
cp .env.example .env
# 編輯 .env,填入你的 GEMINI_API_KEY
# 4. 用 MCP Inspector 測試 Server
mcp dev server.py
# 5. 用 Agent 對話
python agent.py測試結果
MCP Inspector 截圖
貼上 Inspector 的截圖(Tools / Resources / Prompts 三個分頁都要有)
Agent 對話截圖
貼上 Agent 對話的截圖(顯示 Gemini 呼叫 Tool 的過程,以及使用 /use 呼叫 Prompt 的結果)
各 Tool 說明
tool_name(負責:姓名)
功能:
使用 API:
參數:
回傳範例:
@mcp.tool()
def tool_name(param: str) -> str:
"""Tool 的 docstring(這就是 AI 看到的描述)"""
...tool_name(負責:姓名)
功能:
使用 API:
參數:
回傳範例:
tool_name(負責:姓名)
功能:
使用 API:
參數:
回傳範例:
心得
遇到最難的問題
寫下這次實作遇到最困難的事,以及怎麼解決的
MCP 跟上週的 Tool Calling 有什麼不同?
用自己的話說說,做完後你覺得 MCP 的好處是什麼
This server cannot be deployed
Maintenance
Related MCP Connectors
Official MCP server for Agentwork — delegate tasks to AI agents with human-in-the-loop
MCP server for building and testing AI agents with multi-model experimentation and insights.
One AI endpoint to search and call 22k+ MCP servers; 50+ hosted tools work instantly, no key.
Hosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceA lightweight MCP server that enhances AI agents with tools for codebase analysis, task delegation to sub-agents, multi-agent coordination through chatrooms, and project todo management.-
- AlicenseNot gradedqualityBmaintenanceA plugin-based MCP server that enables AI assistants to interact with external systems through custom tools, resources, and prompts.4AGPL 3.0
- AlicenseNot gradedqualityFmaintenanceEnables AI agents to communicate, coordinate, and collaborate on complex tasks through a local MCP server.10 npm8ISC
- AlicenseNot gradedqualityDmaintenanceLocal MCP server that gives AI agents 44 engine tools to build, run, and debug real 2D and 3D games through conversation.MIT