エンドポイントレポート / メタデータとスモークテスト
Microsoft Learn MCP
日時付きのエンドポイント検査です。メタデータと、別途記録されたツール呼び出しには、それぞれ検証データ、範囲、限界を示しています。
以下の原本の証拠と技術的観察は英語のまま掲載しています。
確認できたこと
The anonymous endpoint advertised 3 tools and passed four bounded metadata checks. A separate, fixed read-only smoke scenario is recorded below. Actual ChatGPT and Claude workflows were not tested.
The smoke result applies only to the displayed call and literal content assertions. It does not establish overall answer correctness or reliability.
- 接続とメタデータ
- メタデータ検査に合格
- 観測されたツール一覧
- 全件取得:3 ツール
- 読み取り専用スモークテスト
- 合格 · 1 回の呼び出しを試行
- ChatGPT / Claude
- 未検証 / 未検証
- 総合スコア
- 未採点
読み取り専用スモークテスト / 合格
Fetch the public Azure Functions overview.
固定入力を使った一つの直接ツールテストです。AI モデルや ChatGPT、Claude のセッションは使用していません。試行数にはエラーやタイムアウトになった呼び出しも含みます。
The response passed the registered content assertions.
- スモークテストの呼び出し試行数
- 1
- ツール
- microsoft_docs_fetch
- シナリオとバージョン
- learn-fetch-functions / 1
- 観測日時
- 2026-10-15T07:14:24.660Z
- テストプログラム
- 1.0.0
- プロトコル
- 2025-06-18
- 所要時間
- 171 ms
- 実行 ID
- 904f5c02-9b46-4b29-8cc7-afe25eef5189
- 結果の SHA-256
- 4f5a84cc1d1c1d8a6542946c227f7d09388a188ea2f75554badbc1c3fb39afd7
正確な公開入力
{
"url": "https://learn.microsoft.com/en-us/azure/azure-functions/functions-overview"
}固定入力に対する期待値の判定
- Azure Functions: 合格
- serverless: 合格
記録したレスポンスの抜粋
# What is Azure Functions?
Azure Functions is a serverless solution that allows you to build robust apps while using less code, and with less infrastructure and lower costs. Instead of worrying about deploying and maintaining servers, you can use the cloud infrastructure to provide all the up-to-date resources needed to keep your applications running.
You focus on the code that matters most to you, in the most productive language for you, and Azure Functions handles the rest. For a list of supported languages, see [Supported languages in Azure Functions](supported-languages).
## Scenarios
Functions provides a comprehensive set of event-driven [triggers and bindings](functions-triggers-bindings) that connect your functions to other services without having to write extra code.
The following list includes common integrated scenarios that use Functions.
| If you want to... | then... |
| --- | --- |
| [Process file uploads](functions-scenarios#process-file-uploads) | Run code when a file is uploaded or changed in blob storage. |
| [Process data in real time](functions-scenarios#real-time-stream-and-event-processing) | Capture and transform data from event and IoT so- One fixed public read-only request from a direct MCP client. No model selection, ChatGPT/Claude host, OAuth, private account or write behavior was tested.
- Content assertions check the listed literal terms and absence of a tool error; they do not establish complete factual correctness, relevance or production reliability.
- Observed call duration is one sample and includes network conditions. It is not a latency benchmark or a comparison between services.
- Only the first tools/list page is inspected for this selected tool. No notification stream, redirect, credentials or caller-supplied scenario is allowed.
- Response SHA-256 covers the UTF-8 JSON serialization of the SDK-parsed tool result. Only a bounded public text excerpt is retained; it is untrusted server content.
記録された検査
メタデータ検査の結果です。上にツール呼び出しの結果がある場合も、それとは別の検査です。
protocol-negotiation
Negotiated protocol 2025-06-18; this does not establish host compatibility.
initialized-notification
The initialization notification received HTTP 202 with an empty body.
tool-metadata-shape
SDK metadata shape checked for 3 observed tools. This is not complete JSON Schema validation or behavior verification.
oauth-login
OAuth discovery, login, token refresh and authenticated access are outside this anonymous inspection.
メタデータ取得リクエストの記録
request-1 / initialize
2026-10-15T07:11:36.540Z
HTTP 200 · 573 ms · 1950 B
response-received
request-2 / notifications/initialized
2026-10-15T07:11:37.113Z
HTTP 202 · 170 ms · 0 B
notification-accepted
request-3 / tools/list
2026-10-15T07:11:37.283Z
HTTP 200 · 222 ms · 4950 B
response-received
観測されたツール一覧
ツール名は tools/list で公開されたものです。ツールの実行はスモークテスト欄に別途記録します。
全件取得:3 ツール
- microsoft_code_sample_search
- microsoft_docs_fetch
- microsoft_docs_search
エンドポイントと来歴
- エンドポイント
- https://learn.microsoft.com/api/mcp
- 公式の出典
- https://learn.microsoft.com/en-us/training/support/mcp-developer-reference
- 構成
- Anonymous endpoint profile
- 要求したプロトコル
- 2025-11-25
- 返されたプロトコル
- 2025-06-18
- プロトコル
- 2025-06-18
- 観測日時
- 2026-10-15T07:11:37.511Z
- 実行 ID
- 25dbf005-a320-4ff0-8940-82d00bd453f4
- ツール一覧の SHA-256
- 69a9d1086efe71ee7950a8aa47c0d02c7214485b76d14cc27c7d03bbaa296b60
- 指紋の対象範囲
- complete-catalog
SHA-256 of all observed tool objects, recursively sorted object keys and sorted canonical tool strings; schema array order is preserved. Raw descriptions, schemas and headers are not persisted.
検査の上限
- requestTimeoutMs
- 5,000
- runTimeoutMs
- 30,000
- responseBytes
- 1,048,576
- requests
- 7
- pages
- 5
- tools
- 200
このレポートで確認できていないこと
これらの観察から、一般的なタスク成功、安全性、OAuth の動作、ChatGPT や Claude との互換性を判断することはできません。各テストの限界を確認してください。
- Metadata-only anonymous inspection. No tools/call, OAuth flow, API model calls, host UI or publication review was executed. No global quality or safety score is produced.
- Annotations are server declarations, not verified behavior. Metadata success does not establish task success, security, usefulness or ChatGPT/Claude compatibility.
- Only active exact HTTPS endpoints in the reviewed source registry are accepted. Redirects, supplied credentials, arbitrary endpoints and OAuth URL fetching are disabled. DNS/TLS use the local runtime: this is not a hardened multi-tenant SSRF sandbox and must not be exposed as a public scanner.
- Session identifiers are used only in memory. Request/response headers, raw error messages, raw descriptions and schemas are excluded from artifacts. Tool names and aggregate metadata remain untrusted server input.
- Only the recorded protocol versions and bounded catalog prefix are supported. Reaching a bound or lacking access means unknown, not a failed server or a passing full audit.
MCP の何を改善したいですか?
公開エンドポイントまたはリポジトリ、重要なタスク、利用者のクライアントをお知らせください。パイロットの範囲、アクセス、料金を相談します。
ベンチマークを相談メールアプリが開きます。公開リンクのみを送り、サンドボックスへのアクセスは別途調整してください。