MCP Academy · 课时

使用 Pydantic 定义模型输入

为工具参数定义带类型的结构。

使用 Pydantic 定义模型输入 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。

A Model Per Input

To shape a tool's arguments, you write a Pydantic model: a small class where each attribute is one typed field of the input.

from pydantic import BaseModel

class SearchInput(BaseModel):
    query: str
    limit: int

Subclass BaseModel

Every input model inherits from BaseModel, which gives it parsing, validation, and JSON schema generation for free.

Fields Are Typed Attributes

Each line names a field and its type. Pydantic reads those annotations to know what valid input looks like.

Pass the Model as One Argument

In a FastMCP tool, accept the model as a single typed parameter, and the framework builds the schema from it.

@mcp.tool()
def search(args: SearchInput) -> str:
    return run(args.query, args.limit)

Access Fields by Name

Inside the tool you read values as attributes: args.query and args.limit. No dict lookups, and your editor autocompletes them.

Coercion Where Sensible

Pydantic will gently coerce compatible values, like turning the string 5 into the integer 5, so minor mismatches just work.

Rejecting Bad Types

If a value cannot become the declared type, Pydantic raises a clear validation error instead of letting it slip through.

Nested Models

A field can itself be another model, letting you describe nested objects cleanly instead of deeply nested raw dicts.

class Address(BaseModel):
    city: str

class User(BaseModel):
    name: str
    home: Address

Schema Is Generated

Pydantic turns your model into a JSON schema automatically, which MCP forwards to the client so the model knows the input shape.

Reuse Models Across Tools

Define a model once and share it across several tools. That keeps your input shapes consistent and your code dry.

Type Safety End to End

From the model's call to your function body, the data keeps one verified type, so you never juggle untyped dicts again.

Quick Check

How do you define a typed input shape for a tool with Pydantic?

Recap

Subclass BaseModel, list typed fields, and pass the model as one argument. Pydantic validates input and generates the schema. ✅

常见问题解答

「使用 Pydantic 定义模型输入」课时是免费的吗？

是的 — 「使用 Pydantic 定义模型输入」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。

「使用 Pydantic 定义模型输入」这节课中我会学到什么？

为工具参数定义带类型的结构。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。

「使用 Pydantic 定义模型输入」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。

此课程中的所有课时

← 返回 MCP Academy