What is agentbuilder-outlook-mcp AGENTS.md?

Repository instructions for a Python email server that connects to Microsoft Outlook through Graph, Microsoft's API for Outlook and other services. They describe the code layout, commands, style, and testing rules.

Following the repository structure, installing development dependencies, starting the local server, running pytest tests, validating email payloads, and previewing outgoing mail without sending it.

They give a coding agent the project-specific context needed to make consistent changes and run the right checks.

How jayozer/agentbuilder-outlook-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to jayozer/agentbuilder-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/jayozer/agentbuilder-outlook-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/jayozer/agentbuilder-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/jayozer/agentbuilder-outlook-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/jayozer/agentbuilder-outlook-mcp/agents-md)

Your own site

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

Per session 553 This file is loaded in full into every session.

When invoked 553 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	$0.00553	$0.00553
Opus 5.5	$0.00221	$0.00221
Sonnet 5.5	$0.00111	$0.00111
Haiku 4.5	$0.00055	$0.00055

Measured 2mo ago against content hash 269b875ba794, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agentbuilder-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 2mo 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 · 34 lines

How it starts

The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Module Organization

mcp_outlook/ hosts runtime code: auth.py manages Graph tokens, config.py loads environment variables, and email.py enforces payload validation.
server.py exposes the FastMCP tool declared in fastmcp.json; treat it as the entrypoint for agents.
tests/ mirrors package modules with pytest suites; regenerate build/ and mcp_outlook.egg-info/ only when packaging a release.

Build, Test, and Development Commands

uv pip install .[dev] installs runtime dependencies plus pytest.
fastmcp run server.py starts the stdio MCP server for interactive testing.
pytest (e.g., pytest -k send_mail) executes the suite; add -vv when chasing failures.
Run the dry-run snippet in README.md to preview send_outlook_mail_impl payloads without sending mail.

Coding Style & Naming Conventions

Target Python 3.10+, four-space indentation, and double-quoted strings to stay consistent.
Use type hints and pydantic models for new inputs; prefer raising GraphAuthError/ConfigurationError for domain failures.
Keep functions and variables snake_case, classes PascalCase, and log through module-level loggers.
Reserve comments for intent or edge cases; keep docstrings brief but descriptive when behavior is non-obvious.

Testing Guidelines

Place new tests in tests/ with filenames test_<module>.py and functions beginning with test_.
Mock Microsoft Graph with httpx.MockTransport or fixtures; cover delegated-token and client-credential flows plus validation errors.
Assert on both success payloads and failure messages, and seed os.environ via fixtures when configuration matters.

Commit & Pull Request Guidelines

The scaffold ships without VCS history; follow Conventional Commits (feat:, fix:, docs:) with imperative summaries under 72 characters.
Note configuration changes (env vars, FastMCP metadata) in the commit body and reference related issues in PR descriptions.
PRs should list test evidence (pytest, dry-run preview) and attach payload snippets or logs when changing Graph interactions.

Read the full file on GitHub · 34 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.

2mo ago First seen · 34 lines · 553 tokens per session scan A 269b875ba794

Subscribe to this mod's changes

agentbuilder-outlook-mcp AGENTS.md is an instructions file published in the GitHub repository jayozer/agentbuilder-outlook-mcp (0 stars, last pushed 1y ago), licensed MIT. It adds 553 tokens to every session, about $0.0022 per session on Opus 5.5. 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.

agentbuilder-outlook-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agentbuilder-outlook-mcp AGENTS.mdjayozer/agentbuilder-outlook-mcp	Instructions file	0	1y ago	MIT	A	553	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

agentbuilder-outlook-mcp: Instructions file for Codex