Microsoft Code Reference

Tools

Need	Tool	Example
API method/class lookup	INLINECODE0	INLINECODE1
Working code sample

Finding Code Samples

Use microsoft_code_sample_search to get official, working examples:

CODEBLOCK0

When to use:

- Before writing code—find a working pattern to follow
After errors—compare your code against a known-good sample
Unsure of initialization/setup—samples show complete context

API Lookups

CODEBLOCK1

Fetch full page when method has multiple overloads or you need complete parameter details.

Error Troubleshooting

Use microsoft_code_sample_search to find working code samples and compare with your implementation. For specific errors, use microsoft_docs_search and microsoft_docs_fetch:

Error Type	Query
Method not found	INLINECODE10
Type not found

When to Verify

Always verify when:

- Method name seems "too convenient" (UploadFile vs actual Upload)
Mixing SDK versions (v11 CloudBlobClient vs v12 BlobServiceClient)
Package name doesn't follow conventions (Azure.* for .NET, azure-* for Python)
Using an API for the first time

Validation Workflow

Before generating code using Microsoft SDKs, verify it's correct:

1. Confirm method or package exists — INLINECODE22
Fetch full details (for overloads/complex params) — INLINECODE23
Find working sample — INLINECODE24

For simple lookups, step 1 alone may suffice. For complex API usage, complete all three steps.

CLI Alternative

If the Learn MCP server is not available, use the mslearn CLI from the command line instead:

CODEBLOCK2

MCP Tool	CLI Command
INLINECODE26	INLINECODE27
INLINECODE28

mslearn code-search "..." --language ... |
| microsoft_docs_fetch(url: "...") | mslearn fetch "..." |

Pass --json to search or code-search to get raw JSON output for further processing.

Microsoft 代码参考

工具

需求	工具	示例
API 方法/类查找	microsoftdocssearch	BlobClient UploadAsync Azure.Storage.Blobs
可运行代码示例

查找代码示例

使用 microsoftcodesample_search 获取官方可运行示例：

microsoftcodesample_search(query: upload file to blob storage, language: csharp)
microsoftcodesample_search(query: authenticate with managed identity, language: python)
microsoftcodesample_search(query: send message service bus, language: javascript)

使用时机：

- 编写代码前——查找可遵循的可运行模式
出现错误后——将你的代码与已知正确的示例进行对比
不确定初始化/设置方式——示例展示了完整的上下文

API 查找

验证方法是否存在（包含命名空间以提高精确度）

BlobClient UploadAsync Azure.Storage.Blobs GraphServiceClient Users Microsoft.Graph

查找类/接口

DefaultAzureCredential class Azure.Identity

查找正确的包

Azure Blob Storage NuGet package azure-storage-blob pip package

当方法有多个重载或需要完整的参数详情时，获取完整页面。

错误排查

使用 microsoftcodesamplesearch 查找可运行代码示例并与你的实现进行对比。针对特定错误，使用 microsoftdocssearch 和 microsoftdocs_fetch：

错误类型	查询
方法未找到	[ClassName] methods [Namespace]
类型未找到

何时需要验证

在以下情况始终进行验证：

- 方法名看起来过于方便（UploadFile 与实际 Upload）
混合使用 SDK 版本（v11 CloudBlobClient 与 v12 BlobServiceClient）
包名不符合约定（.NET 的 Azure.，Python 的 azure-）
首次使用某个 API

验证工作流

在使用 Microsoft SDK 生成代码之前，验证其正确性：

1. 确认方法或包存在 — microsoftdocssearch(query: [ClassName] [MethodName] [Namespace])
获取完整详情（针对重载/复杂参数）— microsoftdocsfetch(url: ...)
查找可运行示例 — microsoftcodesample_search(query: [task], language: [lang])

对于简单查找，仅步骤 1 可能就足够了。对于复杂 API 使用，请完成所有三个步骤。

CLI 替代方案

如果 Learn MCP 服务器不可用，请改用命令行的 mslearn CLI：

直接运行（无需安装）

npx @microsoft/learn-cli search BlobClient UploadAsync Azure.Storage.Blobs

或全局安装后运行

npm install -g @microsoft/learn-cli mslearn search BlobClient UploadAsync Azure.Storage.Blobs

MCP 工具	CLI 命令
microsoftdocssearch(query: ...)	mslearn search ...
microsoftcodesample_search(query: ..., language: ...)

mslearn code-search ... --language ... | | microsoftdocsfetch(url: ...) | mslearn fetch ... |

向 search 或 code-search 传递 --json 参数以获取原始 JSON 输出，便于进一步处理。

microsoft-code-reference 微软代码参考