outlook-mcp: Instructions file for Claude Code

CLAUDE.md

outlook-mcp CLAUDE.md is an instructions file for Claude Code from mpalermiti/outlook-mcp. It costs 1,194 tokens per session, scanned A, original, MIT.

An MCP server connects coding assistants to personal Microsoft Outlook accounts through Microsoft Graph, Microsoft's service for accessing Outlook data.

In plain words
What is it for?
It supports local development, testing, formatting, authentication, input validation, pagination, and server startup for an Outlook integration.
Why use it?
It gives an MCP-compatible assistant a defined way to work with Outlook without building the connection from scratch.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code; built for openclaw.

This is mpalermiti/outlook-mcp's own configuration. It tells Claude Code how to work on outlook-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything outlook-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mpalermiti/outlook-mcp. 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/mpalermiti/outlook-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/mpalermiti/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.

agentmods badge for outlook-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mpalermiti/outlook-mcp/claude-md.svg)](https://agentmods.dev/instructions/mpalermiti/outlook-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/mpalermiti/outlook-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/mpalermiti/outlook-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,194 This file is loaded in full into every session.
When invoked 1,194 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01194 $0.01194
Opus 5 $0.00597 $0.00597
Sonnet 5 $0.00239 $0.00239
Haiku 4.5 $0.00119 $0.00119

Measured yesterday against content hash 0d279121eda9, 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 yesterday.

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 · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Outlook MCP Server

What This Is

MCP server for Microsoft Outlook personal accounts (Outlook.com/Hotmail) via Microsoft Graph API. Works with any MCP client (OpenClaw, Claude Code, Cursor).

Tech Stack

  • Python 3.10+, MCP Python SDK 2.x (MCPServer), msgraph-sdk, azure-identity, Pydantic v2
  • Package manager: uv
  • Testing: pytest + pytest-asyncio

Commands

  • uv run pytest — run tests (offline unit suite; integration/live markers are deselected by default)
  • uv run pytest -m live -v — live query-shape guards; run before tagging if you changed any $filter/$orderby/$search construction (see RELEASING.md 1b)
  • uv run pytest -m integration -v — live response-shape smoke tests
  • uv run ruff check src/ tests/ — lint
  • uv run ruff format src/ tests/ — format
  • uv run outlook-mcp — start server (stdio)
  • uv run python scripts/preflight.py — pre-release Graph smoke test (must pass before tagging; see RELEASING.md)

Releasing

Publishing is automated — do not run uv publish or mcp-publisher by hand. Publishing a GitHub release triggers .github/workflows/publish.yml, which re-checks the version lockstep, runs tests and lint, builds, and publishes to PyPI and the MCP registry via GitHub OIDC (no stored credentials). Full process in RELEASING.md. Still manual by design: the live tier (run it before tagging) and ClawHub.

Architecture

  • src/outlook_mcp/server.pyMCPServer entry point, lifespan context
  • src/outlook_mcp/auth.py — Device code OAuth2 via azure-identity
  • src/outlook_mcp/graph.py — Graph client factory
  • src/outlook_mcp/config.py — Config file management (~/.outlook-mcp/)
  • src/outlook_mcp/validation.py — Input validation (OData, KQL, IDs, datetimes)
  • src/outlook_mcp/errors.py — Exception hierarchy
  • src/outlook_mcp/pagination.py — Cursor-based pagination
  • src/outlook_mcp/throttle.py — Retry-After honoring for the raw-httpx delta/$batch paths (SDK path already retries via kiota)
  • src/outlook_mcp/toolsets.py — Tool annotations + config-gated toolset selection (OUTLOOK_MCP_TOOLSETS); configure() runs once after registration
  • src/outlook_mcp/tools/ — One file per tool group:
    • auth_tools.py, mail_read.py, mail_write.py, mail_triage.py — Tier 1
    • calendar_read.py, calendar_write.py — Tier 1
    • contacts.py — Contact CRUD
    • todo.py — To Do task management
    • mail_drafts.py — Draft management
    • mail_attachments.py — Attachment handling
    • mail_folders.py — Folder management
    • mail_thread.py — Threading and copy
    • batch.py — Batch operations
    • user.py — User profile, calendars
    • admin.py — Categories, mail tips
    • inference_overrides.py — Focused Inbox per-sender override CRUD
    • mail_delta.py — Mail delta-sync queries (outlook_list_inbox_delta)
    • calendar_delta.py — Calendar delta-sync queries (outlook_list_events_delta)
    • contacts_delta.py — Contacts delta-sync queries (outlook_list_contacts_delta)
    • _delta.py — Shared httpx-backed delta helper (raw HTTP bypasses the SDK)
    • digest.py — Composed "since last call" digest (outlook_changes_since) wrapping the three delta tools
  • src/outlook_mcp/models/ — Pydantic models for I/O

Read the full file on GitHub · 68 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.

  1. yesterday Changed · +10 lines · +379 tokens per session 0d279121eda9
  2. 6d ago First seen · 58 lines · 815 tokens per session scan A 7635c0ac8628

Subscribe to this mod's changes

outlook-mcp CLAUDE.md is an instructions file published in the GitHub repository mpalermiti/outlook-mcp (24 stars, last pushed yesterday), licensed MIT. It adds 1,194 tokens to every session, about $0.0060 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 2026-08-30.

Related

Other instructions, from other repositories

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

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

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens