A guide for building a custom MCP server on Azure Functions for Copilot Studio. MCP is a protocol that lets an AI agent discover and call tools, while Azure Functions runs those tools in the cloud.

Use it to implement JSON-RPC tool endpoints, verify incoming Entra ID tokens, access services with a managed identity, seed data behind private endpoints, and test deployed routes.

It addresses the protocol, identity checks, private data access, deployment, and connection details needed to let an agent use internal databases, files, or business APIs.

How geekfujiwara/CodeAppsDevelopmentStandard configures Claude Code an

Reuse

Borrowing it

Nothing to install: this file belongs to geekfujiwara/CodeAppsDevelopmentStandard. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/geekfujiwara/CodeAppsDevelopmentStandard/main/.github/skills/mcp-server/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/geekfujiwara/CodeAppsDevelopmentStandard

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/geekfujiwara/codeappsdevelopmentstandard/mcp-server.svg)](https://agentmods.dev/skills/geekfujiwara/codeappsdevelopmentstandard/mcp-server)

Your own site

<a href="https://agentmods.dev/skills/geekfujiwara/codeappsdevelopmentstandard/mcp-server"><img src="https://agentmods.dev/badge/skills/geekfujiwara/codeappsdevelopmentstandard/mcp-server.svg" alt="Measured on agentmods" height="20"></a>

Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,917 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00110	$0.04917
Opus 5	$0.00055	$0.02459
Sonnet 5	$0.00022	$0.00983
Haiku 4.5	$0.00011	$0.00492

Measured yesterday against content hash d618d191720b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

mcp-server scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

The scan reads SKILL.md. This mod also ships 11 executable files (scripts/add_connector_redirect_uri.py, scripts/cleanup_admin_endpoints.py, scripts/configure_connector_oauth.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl では成功するのにコネクタ接続だけが失敗する。

.github/skills/mcp-server/SKILL.md · 268 lines

How it starts

The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Server 開発スキル

Copilot Studio のエージェントから 社内の業務データ（DB・ファイル共有・業務 API） を参照させるための 自前 MCP Server を Azure Functions 上に構築する。

役割分離: VNet / Private Endpoint / Managed Identity といった Azure 基盤の構成は azure スキルに委譲する。本スキルは MCP プロトコル層・Entra 認可・データ投入・ Copilot Studio 登録 を担当する。

設計原則

原則	内容
データ層は非公開、コンピュート層は公開	SQL / Storage は Private Endpoint のみ。Function App の HTTP エンドポイントは公開する（Copilot Studio は SaaS からアウトバウンド接続するため、非公開にすると到達できない）
キーレス	受信 = Entra ID Bearer JWT 検証、送信 = Managed Identity。関数キー・接続文字列・共有キーを使わない
プロトコルは最小実装	`initialize` / `tools/list` / `tools/call` / `ping` のみ。SSE ストリーム・セッション管理は実装しないが、Streamable HTTP の規約には従う（Copilot Studio は Streamable のみ対応）
成否はルート実測で判定	デプロイの終了コードや ARM のメタデータを信用せず、HTTP プローブで実際のルートを確認する
非対話で完走	Azure 操作も `auth_helper` 経由（`az login` を手順に含めない）。→ 認証リファレンス

サブリファレンス

リファレンス	内容
MCP プロトコル最小実装	JSON-RPC 2.0 の実装と Streamable HTTP の必須要件、ツール定義の書き方
認証モデル	受信 JWT 検証 / 送信 Managed Identity の実装
Private 環境でのデータ投入	Private Endpoint 下でシードするための管理エンドポイントパターン
ファイルを読ませるツールの設計	サイドカーテキストレイヤー・パストラバーサル対策・出力上限・プロンプトインジェクション防御
SQL バックエンドのツール設計	パラメータ化クエリ・集計軸のホワイトリスト・トークン寿命と接続プール・読み取り専用権限
Copilot Studio への登録	オンボーディングウィザード、コピペ用 MD 生成、OAuth 接続。OpenAPI 方式もここ
Copilot Studio の DLP 診断	MCP ツールが DLP でブロックされた場合の読み取り診断と最小変更
.env サンプル	本スキルのパラメータ
異常系・トラブルシュート	実際に踏んだ失敗と恒久対策

ワークフロー（正常系）

Step 1: ツール定義を先に確定する

MCP は「エージェントがツール名と入力スキーマだけを見て呼ぶ」ため、実装より先にツール定義を決める。

接続するデータソース（Azure SQL / Azure Files / 業務 API）を列挙する。
データソースごとに 1 つの MCP Server を立てる（責務分割・障害分離のため）。
ツールは 「一覧」「検索」「取得」の 3 系統 を基本形にする。エージェントは一覧で語彙を得てから検索するため、 list_* が無いと的外れな検索語で空振りする。
各ツールの name / description / inputSchema を確定する。→ protocol.md

Read the full file on GitHub · 268 lines

Files

What ships with it

20 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday Changed · +26 lines d618d191720b
2d ago First seen · 242 lines · 110 tokens per session scan A 2dc2b94e975a

Subscribe to this mod's changes

mcp-server is a skill published in the GitHub repository geekfujiwara/CodeAppsDevelopmentStandard (62 stars, last pushed yesterday), licensed MIT. It adds 110 tokens to every session and 4,917 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.

Building agents Cloud DevOps and cloud architecture

architecture-diagram

Dark-themed SVG architecture/cloud/infra diagrams as HTML.

mateaix/mateclaw · 15 tokens

aws-architecture-diagram

AWS architecture diagrams — generate visual network topology diagrams from live AWS infrastructure. Use when drawing AWS network diagrams, visualizing VPCs, mapping Transit Gateway topology, or generating architecture documentation.

automateyournetwork/netclaw · 43 tokens

architecture-paradigm-microservices

Applies microservices for independent deployment and per-service scaling. Use when teams need autonomous release cycles with distinct capability scaling needs.

athola/claude-night-market · 33 tokens

architecture-paradigm-serverless

Applies serverless FaaS patterns for event-driven workloads. Use when designing bursty workloads with minimal infrastructure and pay-per-execution cost model.

athola/claude-night-market · 37 tokens

data-data-lakehouse

Use this skill when designing lakehouse architectures with medallion layers (bronze/silver/gold), Databricks Unity Catalog, Delta Sharing, Apache Paimon, or multi-cloud lakehouse. This skill enforces: medallion architecture layers and data flow, Unity Catalog metastore and RBAC, Delta Sharing for data mesh, Apache…

j4flmao/agent-skills · 113 tokens

omm-push

Push architecture docs to oh-my-mermaid cloud. Handles login, link, and push workflow with error guidance. Use when the user says "omm push", "push to cloud", "deploy architecture", or "share architecture".

oh-my-mermaid/oh-my-mermaid · 49 tokens

CodeAppsDevelopmentStandard: Skill for Claude Code