What is agent365-mcpapp AGENTS.md?

A repository guide describing an MCP app for Microsoft 365 Copilot Chat, including its purpose, commands, architecture, authentication, and main code locations. MCP means Model Context Protocol, a way for AI assistants to use connected tools.

Use it when changing the app, running its TypeScript build or development server, working with Microsoft Graph authentication, or locating tools, widgets, mock data, and clients.

It gives a coding agent the project context needed to work consistently without searching through the repository first. It also records the commands used to build, run, test, and inspect the app.

How Ramakrishnan24689/agent365-mcpapp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Ramakrishnan24689/agent365-mcpapp. 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/Ramakrishnan24689/agent365-mcpapp/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Ramakrishnan24689/agent365-mcpapp

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/ramakrishnan24689/agent365-mcpapp/agents-md/github.svg)](https://agentmods.dev/instructions/ramakrishnan24689/agent365-mcpapp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/ramakrishnan24689/agent365-mcpapp/agents-md"><img src="https://agentmods.dev/badge/instructions/ramakrishnan24689/agent365-mcpapp/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/ramakrishnan24689/agent365-mcpapp/agents-md"><img src="https://agentmods.dev/badge/instructions/ramakrishnan24689/agent365-mcpapp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,078 This file is loaded in full into every session.

When invoked 1,078 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	$0.01078	$0.01078
Opus 5.5	$0.00431	$0.00431
Sonnet 5.5	$0.00216	$0.00216
Haiku 4.5	$0.00108	$0.00108

Measured 2mo ago against content hash b2eec57b5476, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent365-mcpapp 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 · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — AI Assistant Guide for agent365-mcpapp

Project Overview

This is an MCP App (Model Context Protocol) that runs as a Declarative Agent inside Microsoft 365 Copilot Chat. It surfaces Microsoft Agent 365 governance capabilities via Microsoft Graph API with OAuth/OBO authentication, rendering interactive Fluent UI widgets.

Commands

npm run build        # TypeScript check + build widgets + compile server
npm run serve        # Start MCP server (requires .env configured)
npm run dev          # Watch mode (widgets + server)
npm run inspector    # Launch MCP Inspector for testing tools
tsc --noEmit         # Type-check only (no emit)
node build-ui.mjs    # Rebuild widgets only

Architecture

Entry point: main.ts → Express server on port 3001
MCP server: server.ts → registers tools + UI resources via @modelcontextprotocol/ext-apps
Auth: auth.ts → MSAL OBO token exchange (Copilot token → Graph token)
Tools: src/tools/ → each file exports a handler function
Graph clients: src/graph/ → typed fetch wrappers for Graph endpoints
Mock data: src/mock/ → realistic sample data (50 agents)
Widgets: src/widgets/ → React + Fluent UI v9 components
Widget build: Vite + vite-plugin-singlefile → single HTML files in dist/ui/
App manifest: appPackage/ → Teams manifest, agent config, MCP plugin def

Key Patterns

Stateless MCP Server

Each HTTP request creates a fresh McpServer instance with the bearer token from that request. No session state is stored.

Mock vs Live Mode

Controlled by USE_MOCK_DATA env var. The src/graph/client.ts → useMockData() function gates all Graph calls. When mock, tools return data from src/mock/.

Tool + Widget Pairing

Every primary tool has a corresponding widget. The registerToolWithUI() helper in server.ts pairs a tool name with a ui:// resource URI pointing to a built HTML file in dist/ui/.

Widget Architecture

Widgets use useToolData() from @modelcontextprotocol/ext-apps to receive structuredContent from the tool response. They render with Fluent UI v9 components and support the callServerTool() pattern for action tools (block/unblock/reassign).

Read the full file on GitHub · 90 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 · 90 lines · 1,078 tokens per session scan A b2eec57b5476

Subscribe to this mod's changes

agent365-mcpapp AGENTS.md is an instructions file published in the GitHub repository Ramakrishnan24689/agent365-mcpapp (6 stars, last pushed 5mo ago), licensed MIT. It adds 1,078 tokens to every session, about $0.0043 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.

Building agents

agent365-mcpapp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agent365-mcpapp AGENTS.mdRamakrishnan24689/agent365-mcpapp	Instructions file	6	5mo ago	MIT	A	1,078	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	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	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	2d ago	MIT	A	4,313	Codex, OpenCode

agent365-mcpapp: Instructions file for Codex