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.
npx agentmods add instructions/m0nkmaster/msteams-mcp/agents-mdgit clone --depth 1 https://github.com/m0nkmaster/msteams-mcpWrote 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.
[](https://agentmods.dev/instructions/m0nkmaster/msteams-mcp/agents-md)<a href="https://agentmods.dev/instructions/m0nkmaster/msteams-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/m0nkmaster/msteams-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.04416 | $0.04416 |
| Opus 5 | $0.02208 | $0.02208 |
| Sonnet 5 | $0.00883 | $0.00883 |
| Haiku 4.5 | $0.00442 | $0.00442 |
Grade A, and why
msteams-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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guidelines for Teams MCP
Non-obvious project knowledge for AI agents. This is not a tool reference: tool parameters and usage live in the tool definitions (src/tools/*.ts), which are the source of truth and are sent to AI assistants via MCP.
Repository
- Repository: https://github.com/m0nkmaster/msteams-mcp
- Install:
npx -y msteams-mcp@latest, or clone,npm install && npm run build, then point your MCP client atdist/index.js
Project Overview
An MCP (Model Context Protocol) server that lets AI assistants interact with Microsoft Teams. Instead of the Microsoft Graph API, it calls Teams' own APIs (Substrate, chatsvc, CSA) using tokens extracted from a browser session. The browser is only used for initial login; all operations are direct API calls.
Directory Structure
src/
├── index.ts # Entry point, runs the MCP server
├── cli.ts # Standalone CLI (msteams bin) - full tool parity via in-memory MCP transport
├── server.ts # MCP server (TeamsServer class) - delegates to tool registry
├── constants.ts # Shared constants (page sizes, timeouts, thresholds)
├── tools/ # Tool handlers (modular design)
│ ├── index.ts # Tool context and type definitions
│ ├── registry.ts # Tool registry - maps names to handlers
│ ├── search-tools.ts # Search and channel tools
│ ├── message-tools.ts # Messaging, favourites, save/unsave tools
│ ├── people-tools.ts # People search and profile tools
│ ├── meeting-tools.ts # Calendar and meeting tools
│ ├── file-tools.ts # Shared files tools
│ └── auth-tools.ts # Login and status tools
├── auth/ # Authentication and credential management
│ ├── index.ts # Module exports
│ ├── crypto.ts # AES-256-GCM encryption for credentials at rest
│ ├── session-store.ts # Secure session state storage with encryption
│ ├── token-extractor.ts # Extract tokens from Playwright session state
│ ├── token-refresh.ts # Token refresh orchestrator (HTTP-first, browser fallback)
│ └── token-refresh-http.ts # Browserless token refresh via direct OAuth2 calls
├── api/ # API client modules (one per API surface)
│ ├── index.ts # Module exports
│ ├── substrate-api.ts # Search and people APIs (Substrate v2)
│ ├── chatsvc-api.ts # Barrel file re-exporting all chatsvc sub-modules
│ ├── chatsvc-common.ts # Shared utilities (date formatting)
│ ├── chatsvc-messaging.ts # Send, edit, delete, threads, 1:1/group chat
│ ├── chatsvc-activity.ts # Activity feed (mentions, reactions, replies)
│ ├── chatsvc-reactions.ts # Add/remove emoji reactions
│ ├── chatsvc-virtual.ts # Saved messages, followed threads, save/unsave
│ ├── chatsvc-readstatus.ts # Consumption horizons, mark as read, unread
│ ├── csa-api.ts # Favorites API (CSA)
│ ├── calendar-api.ts # Calendar/meetings API
│ ├── transcript-api.ts # Meeting transcripts (Substrate WorkingSetFiles)
│ ├── files-api.ts # Shared files (Substrate AllFiles)
│ └── profile-api.ts # Resolve MRIs to profiles (middleTier fetchShortProfile)
├── browser/ # Playwright browser automation (login only)
│ ├── context.ts # Persistent browser profile management
│ └── auth.ts # Authentication detection and manual login handling
├── utils/
│ ├── parsers.ts # Pure parsing functions (barrel; testable submodules)
│ ├── parsers-reactions.ts # Emoji reaction parsing from raw messages
│ ├── parsers.test.ts # Unit tests for parsers
│ ├── http.ts # HTTP client with retry, timeout, error handling
│ ├── api-config.ts # API endpoints and header configuration
│ └── auth-guards.ts # Reusable auth check utilities (Result types)
├── types/
│ ├── teams.ts # Teams data interfaces
│ ├── errors.ts # Error taxonomy with machine-readable codes
│ ├── result.ts # Result<T, E> type for explicit error handling
│ └── api-responses.ts # Typed interfaces for raw API response shapes
├── __fixtures__/
│ └── api-responses.ts # Mock API responses for testing
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.
- 6d ago First seen · 253 lines · 4,416 tokens per session scan A 6f7f1da8f929
msteams-mcp AGENTS.md is an instructions file published in the GitHub repository m0nkmaster/msteams-mcp (17 stars, last pushed 18d ago), licensed MIT. It adds 4,416 tokens to every session, about $0.0221 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.
Other instructions, from other repositories
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).
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.
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).
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.
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.
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.