What is outlook-mcp CLAUDE.md?

Project instructions for developing the Outlook MCP server, which connects coding tools to Microsoft Outlook through the Graph API. They describe its commands, file structure, coding rules, and tests.

Use them when developing or maintaining this Outlook server, running its tests, working with email or calendar tools, or adding commands.

They give contributors a consistent way to install, authenticate, change, and test the project. They also explain conventions for Outlook data and new tools.

outlook-mcp CLAUDE.md — Instructions file for Claude Code by titanzero: Project instructions for developing the Outlook MCP server, which…

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add instructions/titanzero/outlook-mcp/claude-md

Clone the repo

git clone --depth 1 https://github.com/titanzero/outlook-mcp

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/titanzero/outlook-mcp/claude-md.svg)](https://agentmods.dev/instructions/titanzero/outlook-mcp/claude-md)

Your own site

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

Per session 1,299 This file is loaded in full into every session.

When invoked 1,299 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin fork From a forked repository.

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	$0.01299	$0.01299
Opus 5	$0.00649	$0.00649
Sonnet 5	$0.00260	$0.00260
Haiku 4.5	$0.00130	$0.00130

Measured 5d ago against content hash 36e887892d4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

outlook-mcp 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 5d 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 · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Commands

npm install — always run first
npm start — start MCP server (stdio transport)
npm run auth-server — OAuth server on port 3333 (must be running before auth)
npm run inspect — MCP Inspector for interactive testing
npm test — Jest tests
npm run debug — debug: print env vars and start MCP server
npm run find-folders — find folder IDs via Graph API
npm run move-github — move GitHub emails to subfolder
npm run create-rules — create inbox rules for GitHub notifications
npx kill-port 3333 — free port 3333 if occupied

Cursor Rules Map

.cursor/rules/general.mdc — always-apply core conventions (CommonJS, config centralization, baseline response/error/logging patterns)
.cursor/rules/graph-api.mdc — Graph SDK client usage, fluent API, pagination, and field selection rules
.cursor/rules/toon-responses.mdc — TOON data-shaping and formatter usage
.cursor/rules/new-tool.mdc — workflow and checklist for adding/registering new tools
.cursor/rules/testing.mdc — Jest conventions, mocks, and test structure

Project Structure

index.js              — MCP entry point; imports `authTools`, `calendarTools`, `emailTools`, `folderTools`, `rulesTools` and combines them into `TOOLS`
config.js             — all constants: field selections, pagination, auth, timezone, response format
outlook-auth-server.js — standalone Express OAuth server

auth/
  index.js            — exports `authTools`, `ensureAuthenticated`, `tokenManager`
  tools.js            — auth tool definitions (`about`, `authenticate`, `check-auth-status`)
  token-manager.js    — token load/save/refresh logic
  oauth-server.js     — OAuth callback/exchange helpers

email/                — list, search, read, send, mark-as-read + folder-utils.js
calendar/             — list, create, accept, decline, cancel, delete
folder/               — list, create, move
rules/                — list, create, edit-rule-sequence

utils/
  graph-client.js     — Graph SDK wrapper: `getGraphClient()`, `graphGetPaginated()`
  response-formatter.js — TOON / plain-text toggle (reads `config.RESPONSE_FORMAT`)
  response-helpers.js — `isAuthError()`, `makeErrorResponse()`, `makeResponse()`

scripts/              — CLI & debug one-off scripts (not imported by app modules)
  debug-env.js        — debug: print env vars and start MCP server
  test-config.js      — debug: verify config and token path
  find-folder-ids.js  — CLI: find folder IDs via Graph API
  move-github-emails.js — CLI: move GitHub emails to subfolder
  create-notifications-rule.js — CLI: create inbox rules for GitHub
  backup-logs.sh      — shell: backup Claude Desktop logs
  test-direct.sh      — shell: test server directly via nc
  test-modular-server.sh — shell: test server via MCP Inspector

Read the full file on GitHub · 107 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.

5d ago First seen · 107 lines · 1,299 tokens per session scan A 36e887892d4e

Subscribe to this mod's changes

outlook-mcp CLAUDE.md is an instructions file published in the GitHub repository titanzero/outlook-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 1,299 tokens to every session, about $0.0065 per session on Opus 5. A static security scan graded it A with 0 findings. It comes from a forked repository.

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

outlook-mcp CLAUDE.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

CLAUDE.md

Commands

Cursor Rules Map

Project Structure

What this file has done since we first saw it

Other instructions, from other repositories

vscode buildNext.instructions.md

codex AGENTS.md

vscode oss-third-party-notices.instructions.md

spec-kit AGENTS.md

next.js AGENTS.md

langchain AGENTS.md