添加问候工具
为 Python 函数添加装饰器，让人工智能能够调用它。
添加问候工具 是 CoddyKit 上的免费 MCP Academy 课时。 这是第 2 节课，共 4 节。 你可以在下方免费阅读本课时的完整内容 — 然后在浏览器中使用内置代码编辑器和全天候 AI 导师进行实践。 这是 MCP Academy 学习路径的一部分，你的进度在网页和 CoddyKit 应用中同步。 MCP Academy 课程共包含 4 节课。
本课时的部分内容尚未翻译，以英文显示。
Give Your Server a Skill
A server with no tools is just a shell. A tool is a Python function the AI can call to actually do something for the user. 🛠️
The Magic Decorator
FastMCP exposes a function as a tool with one line: the @mcp.tool() decorator placed right above your function definition.
@mcp.tool()
def hello():
...Write a Normal Function
The body is just Python. No special protocol code, no JSON by hand. You write what the tool should do and return a value.
@mcp.tool()
def hello():
return "Hello from MCP!"Add a Parameter
Tools get more useful with input. Add a parameter and the model can pass a value when it decides to call your tool.
@mcp.tool()
def greet(name):
return "Hello, " + nameType Hints Build the Schema
Add a type hint like name: str and FastMCP turns it into an input schema. The model then knows exactly what kind of value to send.
@mcp.tool()
def greet(name: str) -> str:
return "Hello, " + nameThe Docstring Becomes the Description
Your function's docstring becomes the tool's description. The model reads it to decide when this tool is the right one to use.
@mcp.tool()
def greet(name: str) -> str:
"""Greet a person by name."""
return "Hello, " + nameThe Name Comes from the Function
By default the tool's name is the function name. So def greet publishes a tool the client lists as "greet".
Return Plain Text
For a first tool, just return a string. FastMCP wraps it into the proper MCP result shape so the client receives clean text.
Describe It Well
Good wording matters: a clear description helps the model pick your tool at the right moment. Vague docstrings lead to missed calls.
It Registers Automatically
You never call a register function yourself. Just by decorating it, the tool is registered on your mcp instance and ready to advertise.
Add as Many as You Like
One server can hold many tools. Just decorate each function, and they all show up together when a client asks what's available.
Quick Check
Where does a tool's description come from?
Recap
You added a tool with @mcp.tool(), gave it typed parameters, and let the docstring describe it. Your server can finally do something. Now let's run it! ✨
常见问题解答
「添加问候工具」课时是免费的吗？
是的 — 「添加问候工具」的完整文本可在网页上免费阅读。要进行交互式练习（内置代码编辑器和全天候 AI 导师）并解锁 MCP Academy 课程的其余内容，请升级到 CoddyKit PRO。 MCP Academy 课程共包含 4 节课。
「添加问候工具」这节课中我会学到什么？
为 Python 函数添加装饰器，让人工智能能够调用它。 你通过在浏览器中直接运行的动手代码来练习 MCP Academy，全天候 AI 导师会在你学习这节课的过程中回答你的问题。
学习 MCP Academy 需要有经验吗？
无需任何先前经验。CoddyKit 上的 MCP Academy 课程适合初学者到高级学习者，你可以从这里开始或从头开始，按照自己的节奏学习。 这是第 2 节课，共 4 节。
「添加问候工具」课时需要多长时间？
大多数 CoddyKit 课程大约需要 5–10 分钟。每节课都很精短且互动，所以你能稳步进步，并在网页和应用中从离开的地方继续。
我能在这节 MCP Academy 课中编写并运行代码吗？
能。每节 MCP Academy 课都包含内置代码编辑器，你可以在浏览器中直接编写并运行真实代码，并获得即时 AI 反馈 — 无需本地设置。