m365-radar

m365-radar

An MCP server that provides offline searchable Microsoft 365 roadmap data and live Azure status, enabling AI agents to answer questions about upcoming features, roadmap changes, and Azure incidents.

Category
Visit Server

README

m365-radar

An MCP server and an open daily dataset for the Microsoft 365 roadmap and Azure service status.

Point an AI agent at it and ask what is coming for Intune next quarter, what changed on the roadmap this week, or whether Azure is currently degraded — without anyone opening a browser.

Why a snapshot instead of a live proxy

The roadmap API is undocumented, bot-protected and about 2 MB per request. Querying it on every tool call would be slow and fragile, so this repo does it the other way round:

  1. A GitHub Action harvests the roadmap once a day and commits a normalised snapshot to data/.
  2. The MCP server answers queries from that snapshot — fast, offline-capable, and unaffected if the upstream endpoint has a bad day.
  3. The git history becomes the changelog. The diff between two daily commits is exactly what Microsoft changed on the roadmap, with nothing else in it.

That last point is the radar. git log -p -- data/roadmap.json is a complete, auditable record of roadmap movement over time.

The harvest commits every day so you can see it ran, but the commit message says which kind of day it was: data: roadmap changed … when Microsoft moved something, chore: roadmap unchanged … when they did not.

Tools

Tool What it does
search_roadmap Free-text search with filters for product, status, cloud instance and platform
get_roadmap_item Full detail for one feature ID
list_recent_changes Features added or updated in the last N days — newest first
get_azure_status Active Azure incidents, read live from the public status feed

Statuses are In development, Rolling out, Launched and Cancelled. Cloud instances are Worldwide (Standard Multi-Tenant), GCC, GCC High and DoD.

Use it with Claude Code

git clone https://github.com/DimaVasilenko-Intune/m365-radar.git
cd m365-radar
npm install
npm run harvest   # fetch the first snapshot
npm run build
claude mcp add m365-radar -- node "$(pwd)/dist/server.js"

Any other MCP client works the same way — it is a plain stdio server:

{
  "mcpServers": {
    "m365-radar": {
      "command": "node",
      "args": ["/absolute/path/to/m365-radar/dist/server.js"]
    }
  }
}

The dataset

data/roadmap.json is a normalised array of every published roadmap feature, sorted by ID with a fixed key order so diffs stay clean. data/meta.json records when it was harvested and the full product, platform and cloud-instance taxonomy.

Each feature carries id, title, description, status, products, cloudInstances, platforms, releasePhases, previewDate, generalAvailabilityDate, created, modified, moreInfoLink and a url deep link.

The data is Microsoft's; this repo only reshapes it. Use it for whatever you like.

Your clone does not refresh itself. This repository is updated daily, but a checkout on your machine stays at whatever commit you pulled. Every tool response reports snapshotAgeDays, and once your copy is three days old it also returns a warning telling you to git pull or run npm run harvest. Keeping it current is a pull, or a git pull on a schedule if you would rather not think about it.

Data sources

Source Endpoint
Microsoft 365 roadmap https://www.microsoft.com/releasecommunications/api/v1/m365
Azure status https://azure.status.microsoft/en-us/status/feed/

Be aware: the roadmap endpoint is not a documented, supported API. It returns 403 unless the request carries a browser User-Agent, and Microsoft can change or withdraw it without notice. The snapshot design means a bad upstream day costs you freshness, not availability — the harvest refuses to overwrite a good snapshot with an empty or malformed response.

No tenant data, no authentication and no Microsoft Graph calls are involved anywhere in this project. Everything here is public information.

Development

npm run harvest   # refresh data/ from upstream
npm run dev       # run the server from source
npm run build     # compile to dist/

License

MIT © Dima Vasilenko

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured