What is microsoft-mcp-server CLAUDE.md?

A set of Claude Code instructions for developing a Microsoft Graph MCP server. Microsoft Graph is Microsoft's API for Microsoft 365 data such as users, email, calendars, and files.

Use it when modifying, testing, building, or running the sapientsai/microsoft-mcp-server repository. The documented validation command runs formatting, linting, tests, and a build.

It gives the coding agent the repository's development commands, architecture, authentication approach, and main components so it can work consistently in the project.

How sapientsai/microsoft-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to sapientsai/microsoft-mcp-server. 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/sapientsai/microsoft-mcp-server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/sapientsai/microsoft-mcp-server

Made for: Claude Code.

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/instructions/sapientsai/microsoft-mcp-server/claude-md.svg)](https://agentmods.dev/instructions/sapientsai/microsoft-mcp-server/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/sapientsai/microsoft-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/sapientsai/microsoft-mcp-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 604 This file is loaded in full into every session.

When invoked 604 The same file — it is already loaded in full.

Security scan A 0 findings. 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	$0.00604	$0.00604
Opus 5	$0.00302	$0.00302
Sonnet 5	$0.00121	$0.00121
Haiku 4.5	$0.00060	$0.00060

Measured 6d ago against content hash e24b7d8e1f0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

microsoft-mcp-server CLAUDE.md scanned grade A with 0 findings 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 6d ago.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Microsoft Graph MCP Server - A Model Context Protocol server built with FastMCP that provides AI assistants access to Microsoft Graph API for Microsoft 365 services (users, mail, calendar, files, etc.).

Development Commands

pnpm validate        # Main command: format + lint + test + build (use before commits)

pnpm test            # Run tests once
pnpm test -- --testNamePattern="pattern"    # Filter by test name
pnpm test -- test/specific.spec.ts          # Run specific file

pnpm build           # Production build
pnpm dev             # Development build with watch mode
pnpm start           # Run the server (requires build first)

Architecture

Built with FastMCP - a TypeScript framework for MCP servers.

src/
├── index.ts          # Server factory, config, tools, exports
└── bin.ts            # CLI entry point (shebang, dotenv, runServer)

Key Components

FastMCP: Server framework handling MCP protocol, sessions, transport
AzureProvider: OAuth 2.0 authentication with Azure AD/Entra ID
Tools: microsoft_graph (Graph API calls) and get_auth_status (check auth)

Authentication Flow

OAuth 2.0 handled by FastMCP's AzureProvider:

MCP client (Claude Desktop) initiates OAuth when tool requires auth
User redirected to Microsoft login
Callback to {BASE_URL}/oauth/callback
Token stored in session, passed to tools via session.accessToken

Transport Modes

httpStream (default): HTTP server with /mcp endpoint and /oauth/callback
stdio: For Claude Code CLI integration

Configuration

Required environment variables:

AZURE_CLIENT_ID=...      # Azure app registration client ID
AZURE_CLIENT_SECRET=...  # Azure app client secret
AZURE_TENANT_ID=common   # Tenant ID (default: "common" for multi-tenant)
BASE_URL=http://localhost:8080  # Server URL (for OAuth callback)
PORT=8080                # Server port
TRANSPORT_TYPE=httpStream  # httpStream or stdio

Read the full file on GitHub · 75 lines

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.

6d ago First seen · 75 lines · 604 tokens per session scan A e24b7d8e1f0b

Subscribe to this mod's changes

microsoft-mcp-server CLAUDE.md is an instructions file published in the GitHub repository sapientsai/microsoft-mcp-server (1 stars, last pushed 2mo ago), licensed MIT. It adds 604 tokens to every session, about $0.0030 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

microsoft-mcp-server: Instructions file for Claude Code