What is teams-mcp-server CLAUDE.md?

A set of instructions for developing teams-mcp-server, an MCP server that connects to Microsoft Teams through Microsoft Graph, Microsoft's API for its services.

Use it when developing or testing the Teams server, configuring Azure authentication, or understanding how its files connect to Microsoft Graph.

It gives contributors the project's technology choices, commands, configuration, and architecture in one place.

How ssasuoirafen/teams-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ssasuoirafen/teams-mcp-server. 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/ssasuoirafen/teams-mcp-server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/ssasuoirafen/teams-mcp-server

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ssasuoirafen/teams-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/ssasuoirafen/teams-mcp-server/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/ssasuoirafen/teams-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/ssasuoirafen/teams-mcp-server/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/ssasuoirafen/teams-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/ssasuoirafen/teams-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,772 This file is loaded in full into every session.

When invoked 1,772 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	$0.01772	$0.01772
Opus 5	$0.00886	$0.00886
Sonnet 5	$0.00354	$0.00354
Haiku 4.5	$0.00177	$0.00177

Measured 8d ago against content hash 0411699f97bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

teams-mcp-server 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 8d 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 · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Teams MCP Server

MCP server for Microsoft Teams via Microsoft Graph API. Delegated auth (device code flow), no client secret.

Stack

Python >=3.12 (dev pin: 3.14 via .python-version), mcp[cli] (FastMCP API), httpx, msal. Registration-count smoke test in tests/ (uv run pytest); ruff + pytest in the dev group (uv sync). CI runs on push/PR via .github/workflows/ci.yml (uv sync + pytest + advisory ruff).

Commands

uv run teams-mcp              # run server (needs TEAMS_MCP_TENANT_ID, TEAMS_MCP_CLIENT_ID)

Environment Variables

TEAMS_MCP_TENANT_ID (required) - Azure AD tenant ID
TEAMS_MCP_CLIENT_ID (required) - App registration client ID
TEAMS_MCP_SCOPES (optional) - comma-separated scope override (default: .default; scope semantics in the Scopes section)

Architecture

Three-file pattern, all logic flows through the same pipeline:

server.py (MCP tools) -> graph.py (Graph API client) -> Microsoft Graph REST API
                          auth.py (MSAL device code flow, token cache)

src/teams_mcp/auth.py - AuthManager: device code flow, token cache at ~/.teams-mcp/token_cache.json. Default scope https://graph.microsoft.com/.default (semantics in the Scopes section)
src/teams_mcp/graph.py - GraphClient: async httpx wrapper with _get, _post, _post_no_content, _patch, _delete helpers. All raise GraphApiError on failure (parses Graph API JSON error body). GRAPH_BASE constant points at v1.0 — all endpoints currently used are GA.
src/teams_mcp/server.py - MCP tools + response post-processing (Adaptive Card text extraction, forwarded/quoted message parsing, hosted-content inlining, mention parsing). Global auth/graph initialized lazily. _require_auth() guard on every tool.

Tools

Auth

login / complete_login - device code flow (two-phase)

Read

list_teams, list_channels, list_chats
list_channel_messages, list_chat_messages, list_thread_replies
list_team_members, list_channel_members, list_chat_members
list_team_tags (tag ids for @tag mentions; needs TeamworkTag.Read)
list_pinned_messages
get_user_presence, get_user (search by name/email)
search_messages (Microsoft Search API, full-text)
download_attachment (inline images via hostedContents, magic-byte format detection — png/jpg/gif/webp, returns temp file path)

Read the full file on GitHub · 111 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.

8d ago First seen · 111 lines · 1,772 tokens per session scan A 0411699f97bf

Subscribe to this mod's changes

teams-mcp-server CLAUDE.md is an instructions file published in the GitHub repository ssasuoirafen/teams-mcp-server (0 stars, last pushed yesterday), licensed MIT. It adds 1,772 tokens to every session, about $0.0089 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 2026-09-01.

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

teams-mcp-server: Instructions file for Claude Code