agentmods.dev

owa-exchange-mcp: Instructions file for Claude Code

CLAUDE.md

owa-exchange-mcp CLAUDE.md is an instructions file for Claude Code from nhype/owa-exchange-mcp. It costs 631 tokens per session, scanned A, original, MIT.

Repository instructions for an MCP server that connects AI agents to Microsoft Exchange through Outlook Web Access, the web version of Outlook. The server covers email, calendars, contacts, availability, meetings, and login sessions.

In plain words
What is it for?
Use them when configuring, running, or extending the server, including its browser login, cookie handling, OWA client, and tool modules.
Why use it?
They explain the project structure, required settings, authentication, and supported Exchange-related areas before code changes are made.

Instructions file for Claude Code

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

This is nhype/owa-exchange-mcp's own configuration. It tells Claude Code how to work on owa-exchange-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 owa-exchange-mcp configures →

not rated 8repo 6mo ago A scan 631 tokens original MIT
View source ↗ nhype/owa-exchange-mcp
Reuse

Borrowing it

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

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nhype/owa-exchange-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/nhype/owa-exchange-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/nhype/owa-exchange-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/nhype/owa-exchange-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for owa-exchange-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/nhype/owa-exchange-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/nhype/owa-exchange-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 631 This file is loaded in full into every session.
When invoked 631 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 $0.00631 $0.00631
Opus 5 $0.00316 $0.00316
Sonnet 5 $0.00126 $0.00126
Haiku 4.5 $0.00063 $0.00063

Measured 9d ago against content hash 5dc33e3412b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

owa-exchange-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 9d 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 · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 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

Exchange MCP is a Model Context Protocol server for any Microsoft Exchange / OWA (Outlook Web Access) deployment. It gives LLM agents full access to email, calendar, directory, availability, and meeting analytics over the standard OWA JSON API. Works with any on-premise or hosted Exchange server that exposes OWA.

Configuration

The server requires two environment variables:

  • EXCHANGE_OWA_URL — Base URL of the OWA instance (e.g. https://owa.example.com)
  • EXCHANGE_COOKIE_FILE — (optional) Path to session cookies file. Defaults to session-cookies.txt next to the package.

Structure

  • login.py — Browser-based login via 2FA, saves session cookies
  • exchange_mcp/ — MCP server package (20 tools)
    • server.py — FastMCP server with lifespan context (tolerates missing cookies at startup)
    • owa_client.py — Centralized OWA HTTP client
    • auth.py — Async Playwright login logic, cookie encryption/decryption (reuses crypto from login.py)
    • tools/ — Tool modules: email, calendar, people, folders, availability, analytics, auth

Running

export EXCHANGE_OWA_URL=https://owa.example.com

python3 login.py --setup   # One-time credential setup
python3 login.py            # Login (creates session-cookies.txt)
pip install -e .             # Install MCP server
exchange-mcp-server          # Run MCP server (stdio transport)

Dependencies: mcp, requests, cryptography, playwright (for login).

Architecture

Session-based workflow: login.py (CLI) or the login MCP tool authenticates via browser-based 2FA and saves encrypted cookies to session-cookies.txt. The login tool decrypts cookies into memory; the server never reads plaintext cookies from disk. The server starts without cookies; the login tool can authenticate within the MCP session.

OWA JSON API pattern:

  1. Decrypt cookies from session-cookies.txt (encrypted with master password)
  2. Extract X-OWA-CANARY token for CSRF protection
  3. POST JSON to $EXCHANGE_OWA_URL/owa/service.svc?action=<ACTION>
  4. Request bodies use EWS __type annotations (e.g. "CalendarItem:#Exchange")
  5. HTTP 401/440 = session expired → call the login tool or rerun login.py

Read the full file on GitHub · 52 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. 9d ago First seen · 52 lines · 631 tokens per session scan A 5dc33e3412b6

Subscribe to this mod's changes

owa-exchange-mcp CLAUDE.md is an instructions file published in the GitHub repository nhype/owa-exchange-mcp (8 stars, last pushed 6mo ago), licensed MIT. It adds 631 tokens to every session, about $0.0032 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.

Backend and APIs
Related

Other instructions, from other repositories

vibe-coding-prompt-template backend.instructions.md

Instructions for KhazP/vibe-coding-prompt-template: Read AGENTS.md, agentdocs/techstack.md, and agentdocs/codepatterns.md.

KhazP/vibe-coding-prompt-template · 139 tokens

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 · 5,153 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