MCP Academy · 课时

从代码调用工具

调用服务器工具并读取其结果。

从代码调用工具 是 CoddyKit 上的免费 MCP Academy 课时。这是第 3 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。

From Listing to Doing

Discovery told you what exists. Now you actually invoke a tool, sending arguments and reading back the result from your own code.

Call by Name

Use session.call_tool() with the tool name and a dictionary of arguments. The names must match the inputSchema you discovered.

result = await session.call_tool(
    "add",
    {"a": 2, "b": 3},
)

Arguments Must Validate

Your arguments dictionary should satisfy the tool inputSchema. Sending the wrong shape leads the server to reject the call.

await session.call_tool("greet", {"name": "Ada"})

Read the Content

The result carries a content list of blocks. Most tools return text, so you read the text off the first block.

print(result.content[0].text)

Check for Errors

A tool that fails sets isError to true on the result instead of raising. Inspect it so your client can react gracefully.

if result.isError:
    print("tool failed")

Structured Output Too

Newer tools may also return structuredContent, a typed object alongside the text, when the server defines an output schema.

print(result.structuredContent)

Pass Real Arguments

Arguments come from your program, a user, or a model. The client simply forwards them as a plain dict to the named tool.

args = {"city": "Paris"}
await session.call_tool("weather", args)

It Is Still Async

Like every network call, call_tool is awaited. The await pauses until the server finishes the work and the result returns.

One Call, One Result

Each invocation is a request-response pair. The session matches the reply to your request by id, so results never get crossed.

Handle Slow Tools

Some tools take time. A robust client sets a timeout so a hung tool does not freeze your whole program.

You Are the Orchestrator

Calling tools from code means your program decides the order, combines results, and turns raw output into something useful for the user.

Quick Check

How do you run a discovered tool from client code?

Recap: Making the Call

You invoked tools end to end: call by name with valid arguments, read the content blocks, and check isError before trusting the output.

常见问题解答

「从代码调用工具」课时是免费的吗？

是的 — 「从代码调用工具」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。

「从代码调用工具」这节课中我会学到什么？

调用服务器工具并读取其结果。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 3 节课，共 4 节。

「从代码调用工具」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。

此课程中的所有课时

← 返回 MCP Academy