What is mariana-outlook-mcp AGENTS.md?

Repository instructions for mariana-outlook-mcp, a local server that lets coding agents work with Microsoft Outlook mail, calendars, and contacts through Microsoft Graph. They document its safety rules and code layout.

Use them when modifying authentication, Microsoft account access, mail, calendar, contacts, configuration, or action logging in this repository.

They help contributors understand the project and avoid weakening safeguards, such as preventing direct sending or permanent deletion. They also flag related changes that may need to be made in the sibling Google server.

How marianasmall/mariana-outlook-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to marianasmall/mariana-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/marianasmall/mariana-outlook-mcp/main/AGENTS.md

Clone the repo

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

Made for: Codex, OpenCode.

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/marianasmall/mariana-outlook-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/marianasmall/mariana-outlook-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/marianasmall/mariana-outlook-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/marianasmall/mariana-outlook-mcp/agents-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/marianasmall/mariana-outlook-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/marianasmall/mariana-outlook-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 551 This file is loaded in full into every session.

When invoked 551 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	$0.00551	$0.00551
Opus 5	$0.00275	$0.00275
Sonnet 5	$0.00110	$0.00110
Haiku 4.5	$0.00055	$0.00055

Measured 10d ago against content hash 4a6087283588, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mariana-outlook-mcp AGENTS.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 10d 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.

AGENTS.md · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — mariana-outlook-mcp

What this repo is

Custom MCP server giving Claude Code safety-first access to Microsoft accounts (Outlook Mail, Calendar, Contacts) via Microsoft Graph. Sibling of mariana-google-mcp — same architecture, same safety guarantees, Microsoft instead of Google. When changing one sibling, check whether the change belongs in both.

Safety architecture (do not weaken)

No send: Mail.Send scope is never requested (src/auth.ts SCOPES). Never add it.
No delete: mail soft-deletes to a "To Be Deleted" folder; calendar prepends "DELETE - ". Never call Graph DELETE on mail/events.
Action log: every mutating tool calls logAction() (JSONL at ~/.config/mariana-outlook-mcp/action-log.jsonl).
PKCE public client: no client secret exists anywhere. MS_CLIENT_ID env var is the only credential config.

Where things live

src/index.ts — server + microsoft_auth / microsoft_status
src/auth.ts — PKCE OAuth flow (non-blocking consent, live token health, refresh-token rotation)
src/graph.ts — minimal fetch wrapper for Graph v1.0
src/mail.ts / src/calendar.ts / src/contacts.ts — tool modules
src/config.ts — account registry, email-hash token paths (~/.config/mariana-outlook-mcp/)
SETUP-PROMPT.md — paste-into-Claude-Code install doc (public; person-agnostic — keep it that way)

Rules

Tokens are stored under sha256(email) filenames; the config file never holds plaintext addresses.
Build with npm run build (tsc, strict). dist/ is gitignored — consumers build from source.
Tool descriptions are user-facing contracts; keep caveats (attendee notifications, moved-message IDs, 3MB attachment cap) in them.
README tool table must be updated in the same commit as tool changes.

Gotchas

Graph $search disallows $orderby; $filter on calendarView uses single-quote escaping ('').
createReply produces the draft first; body/recipients are PATCHed onto it after.
Graph small attachments (contentBytes) cap at ~3MB/file; bigger needs upload sessions (not implemented).
Microsoft rotates refresh tokens — always persist the new one after refresh (toStored handles this).

Read the full file on GitHub · 36 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.

10d ago First seen · 36 lines · 551 tokens per session scan A 4a6087283588

Subscribe to this mod's changes

mariana-outlook-mcp AGENTS.md is an instructions file published in the GitHub repository marianasmall/mariana-outlook-mcp (0 stars, last pushed 20d ago), licensed MIT. It adds 551 tokens to every session, about $0.0028 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 · 5,153 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

mariana-outlook-mcp: Instructions file for Codex