How do I install Microsoft Graph MCP?

Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.

Does Microsoft Graph MCP need an API key?

The publisher lists these environment variables: MICROSOFT_GRAPH_BASE_URL, MICROSOFT_GRAPH_TOKEN, MICROSOFT_GRAPH_HOME_TENANT, MICROSOFT_GRAPH_TRANSCRIPTS_APP_ONLY, MICROSOFT_GRAPH_MCP_NO_TRANSCRIPTS, MICROSOFT_GRAPH_MCP_READ_ONLY, MICROSOFT_GRAPH_NO_LOCAL_DATA, MICROSOFT_GRAPH_USER_AGENT, PRINTING_PRESS_CLIENT_PROFILE, MICROSOFT_GRAPH_MCP_HTTP_TOKEN.

What transport does Microsoft Graph MCP use?

Microsoft Graph MCP runs locally over stdio.

When was Microsoft Graph MCP last checked?

Last checked 2026-11-09. The maintained single-binary successor to the retiring mgc - every MSP-relevant Microsoft Graph

Microsoft Graph MCP server

Run your MSP tools by asking - MCP servers and Skills for the AI you already use

MSP Skills connects your PSA, RMM, backup, and more to the AI you already use - Claude, ChatGPT, Codex, Cursor, Windsurf, or any agent that speaks MCP. Ask a plain-English question about your stack and get a real answer back.

84 connectors are live today - including Servosity, ConnectWise PSA, HubSpot, and HaloPSA - and more PSA, RMM, backup, and M365 connectors ship every week.

Free, open source, runs on your laptop. A local SQLite mirror lets your agent answer cross-client questions the live API can't return in one shot - no rate-limit hits, no per-tech SaaS fee, and your data stays local unless you route it somewhere yourself. Built for MSP owners. No developer experience required.

New to the term? What this repo calls an MCP server is what ChatGPT calls an app or connector, Claude on the web calls a connector, Microsoft Copilot calls a connector, and Claude Code calls a Skill. Same standard underneath: the Model Context Protocol. Full plain-language answer: What is an MCP server?.

First time here? Paste this into Claude Code

You do not need to know which command does what. Open Claude Code and paste:

Set up msp-skills for me from https://github.com/servosity/msp-skills. Read the repo's README, install the connectors that fit my stack, and walk me through anything only I can do (like approving a browser extension or signing in to a vendor portal).

Two notes that save the most time, on Windows and macOS alike:

Adding the marketplace by its full HTTPS URL avoids an SSH key a fresh machine does not have:
```
/plugin marketplace add https://github.com/servosity/msp-skills.git
/plugin install connect-tool@msp-skills
```
The .git suffix matters.
Windows works. Claude Code runs natively on Windows, and Git for Windows is optional. If you do not have Git, connect-tool installs without it:
```
irm https://raw.githubusercontent.com/servosity/msp-skills/main/skills/connect-tool/bootstrap.ps1 | iex
```

Stuck on credentials? That is what connect-tool is for: it drives the Chrome you are already logged into, puts the API key straight into Windows Credential Manager or the macOS Keychain, and refuses to say "connected" until a real authenticated call returns your live data.

What's in the box

⭐ First-party, by Servosity: the servosity backup & DR connector + the guided concierge and the connect-tool.

Skill	System	Install
⭐ msp-skills-concierge	Connector recommendations + guided install for the msp-skills catalog	Marketplace
abnormal	cloud email security platform that detects and remediates phishing, business email compromise, account takeover, and vendor email compromise	Install
acronis	Acronis Cyber Protect Cloud	Install
action1	Patch management and vulnerability remediation across managed endpoints in every client organization	Install
afi	SaaS backup for Microsoft 365 and Google Workspace	Install
appdirect	AppDirect cloud commerce marketplace	Install
atera	all-in-one RMM, PSA, and remote-access platform for MSPs and internal IT teams	Install
autotask

About the badges. Live-verified (green) means a real MSP confirmed this skill against a live production tenant - the badge carries the date and source. Awaiting live verification (amber) means it passes every mechanical gate (build, command-surface-vs-docs claims check, install dry-run) but no one has reported a live run yet - be the first: run it against your tenant and report that it works.

🛠 Built live with MSPs. Join a free weekly Build Session at compoundingteams.com/build-sessions to watch a Skill built against a real MSP system - or bring your own.

Install in 60 seconds

Path A - paste one prompt into your AI agent (recommended)

Not sure which connector to pick? Let your agent decide. Paste this into Claude Code, Codex CLI, or Claude Cowork:

Read https://github.com/Servosity/msp-skills and, using everything you know about me and how my MSP works, recommend which connectors I should install - then install the ones I approve.

Prefer a guided version? The concierge does the same from inside Claude Code: /plugin marketplace add Servosity/msp-skills, then /plugin install msp-skills-concierge@msp-skills.

Or install a specific connector. The Servosity prompt:

Install the Servosity Skill and MCP server from Servosity/msp-skills in this agent workspace. If this workspace uses a POSIX shell (macOS, Linux, WSL, or Bash), run bash <(curl -fsSL https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/servosity/install.sh). If it uses Windows PowerShell, run iwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/servosity/install.ps1 | iex. Then authenticate with SERVOSITY_MSP_TOKEN=<your-partner-token> servosity-cli doctor and run servosity-cli --help to explore.

And the ConnectWise PSA (Manage) prompt:

Install the ConnectWise PSA (Manage) Skill and MCP server from Servosity/msp-skills in this agent workspace. If this workspace uses a POSIX shell (macOS, Linux, WSL, or Bash), run bash <(curl -fsSL https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/connectwise-manage/install.sh). If it uses Windows PowerShell, run iwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/connectwise-manage/install.ps1 | iex. Then authenticate per the README and run connectwise-manage-cli --help to explore.

The same prompt works for every connector in the table above - swap the skill name and slug. If your agent can't run shell, use Path B below.

Path B - run the installer yourself

On macOS / Linux (swap the slug for any connector in the table above):

bash <(curl -fsSL https://raw.githubusercontent.com/servosity/msp-skills/main/skills/servosity/install.sh)

On Windows (PowerShell):

iwr -useb https://raw.githubusercontent.com/servosity/msp-skills/main/skills/servosity/install.ps1 | iex

Each installer drops both the CLI and the MCP server, so you can use the Skill (Claude Code / Codex) and the MCP server (Claude Desktop / ChatGPT / Cursor / etc.) from one install. For Claude Desktop, ChatGPT, Cursor, Windsurf, Cline, Continue, Gemini, or Copilot wire-up, see docs/which-agent.md and each skill's mcp-install.md.

Now what? Once your connector's --version (or doctor) returns clean, you're 60 seconds from your first real query. Bring your tenant + your hardest cross-client question to a free Build Session - we'll work it live with the MSP cohort and the same Skills you just installed.

What your agent can do

Outcomes, not hype - drawn from each of the 84 connectors' skill pages:

Outcome	Skill	Command
What new, unremediated email threats need attention right now?	abnormal	`abnormal-cli triage --since 24h --top 20`
Whose backups succeeded, failed, or went stale across every customer last night?	acronis	`acronis-cli health`
Which endpoints across all clients are missing the most patches?	action1	`action1-cli fleet patch-posture`
Which resources have no backup protection at all?	afi	`afi-cli coverage-gaps --agent`
Which payments failed or stalled in the last week, across every company?	appdirect	`appdirect-cli payments unpaid --since 7d --json`
Which agents have gone offline or stopped checking in?	atera	`atera-cli agents stale --days 30`
Which approved time entries haven't been invoiced yet?	autotask	`autotask-cli unbilled`
What hardware is past or approaching end-of-support across every client?	auvik	`auvik-cli eol --bucket expired`
What did Avanan catch across my tenants since the start of my shift?	avanan	`avanan-cli triage --since 24h`
Why did my bill change month-over-month?	aws-billing	`aws-billing-cli compare --from last-month --to this-month`
Whose backups failed or went stale across every client last night?	axcient	`axcient-cli health`
Which backups are failing or silent today, new or ongoing, and how many tickets are open on each?	backup-radar	`backup-radar-cli check --agent`
What's down right now and is anyone actually paged?	betterstack	`betterstack-cli down`
Which customers have unmanaged, outdated or unscanned endpoints?	bitdefender	`bitdefender-cli fleet health`
What are the worst open findings across all my client accounts right now?

Cross-skill questions compose too: find every ticket about backup failures across all clients by combining halopsa-cli tickets search with servosity-cli stale-backups.

Works with your agent

The five agents MSP owners actually use:

Your AI agent	Why MSPs use it	How to install MSP Skills
Claude Desktop (Mac/Windows app)	The most common MSP-owner choice - no terminal, just a chat window	Run installer, then Settings > Extensions to register the MCP server
ChatGPT (paid plans)	The brand most MSPs already pay for; pair with Developer Mode	Run installer, expose MCP over HTTPS, register as a Developer Mode connector
Claude Code (CLI)	For the technical-leaning MSP owner or your senior tech	Paste the install prompt above
Codex CLI (OpenAI)	OpenAI's terminal agent for the same audience	Paste the install prompt above
Claude Cowork (Anthropic, GA Mar 2026)	Desktop agent that runs shell on your behalf	Paste the install prompt above

Also works with Cursor, Windsurf, Cline, Continue.dev, Zed, GitHub Copilot, and Gemini CLI. MSP Skills speaks the open MCP standard, so any current or future MCP-capable agent can use it. Full per-tool deep-dive: docs/which-agent.md.

Run more than one agent? Install MSP Skills across all 51+ supported agents at once: npx skills add Servosity/msp-skills@latest (requires Node.js, then run the per-skill installer for the CLI/MCP binaries). Details in docs/which-agent.md.

What makes this different

Local mirror, not live calls

Most AI tools and MCP servers for PSAs and backup systems call the vendor's API on every question your agent asks. That works fine for "show me ticket #4421." It falls over at QBR time, when you're asking "how many backup-failure tickets across all 47 clients last quarter, grouped by engine?" - that's 47 paginated REST calls, rate-limit headaches, and a context window full of raw JSON the model has to re-read.

MSP Skills syncs each connected system into a local SQLite mirror with full-text search. Cross-client and cross-engine questions become one local query: instant, offline, and the AI sees the answer, not the raw data.

Works with the AI you already use

You don't have to switch agents to use MSP Skills. Same package, two interfaces: a Claude Code / Codex Skill for shell-style agents, and an MCP server for Claude Desktop, ChatGPT, Cursor, Windsurf, Cline, Continue.dev, Gemini, and Copilot. One install drops both binaries on your machine. Use one or both - your call. No vendor lock-in, no proprietary plugin format, no SaaS subscription that ties you to a single AI.

MSP owner first, not developer first

You don't have to know JSON, regex, or what "stdio transport" means. Paste one sentence into Claude Code or Codex and your agent reads the Skill, installs the binary, and walks you through authentication. Every command has a tier (read / write / destructive) and a recommended agent policy in each skill's governance.md - reads are always safe, and the recommended agent rule is to preview writes with --dry-run and require your approval before any mutation. The hard stuff is hidden; the safety bar is high.

Safety model

These skills hold privileged, multi-tenant access to systems that run MSP businesses, so safety is a first-class concern, not a footnote:

You supply your own credentials at runtime. Nothing is stored in this repo.
Every skill ships a permission matrix. Each skill's governance.md tags commands read / write / destructive and tells you how to scope an agent. The safe default for an autonomous agent is read plus previewed writes (--dry-run first, human approval before the real thing); gate destructive and credential-touching operations behind a human.

Frequently asked questions

Does this work with ChatGPT?

Yes, on Plus, Pro, Team, Business, Enterprise, and Education plans (Free tier does not yet expose Developer Mode). ChatGPT connects to remote MCP servers over HTTPS, not to local binaries directly. MSP Skills ships local binaries. Most of them serve Streamable HTTP themselves - run one with --transport http and put its /mcp endpoint behind an HTTPS tunnel; the six stdio-only connectors go behind a supergateway bridge instead. Step-by-step, per connector: each skill's mcp-install.md.

Does this work with Claude?

Yes - Claude Code, Claude Desktop, and Claude.ai web (via Claude Desktop's MCP). Claude Code reads the Skill directly. For Claude Desktop, run the installer, then go to Settings > Extensions to register the MCP server - the panel walks you through it without editing JSON. (Power users can still hand-edit claude_desktop_config.json via Settings > Developer > Edit Config if you prefer.) Both paths are first-class.

Is my PSA, CRM, or backup data safe? Does it leave my network?

Your data stays on your machine. MSP Skills runs locally: the CLI and the MCP server are binaries on your laptop. The SQLite mirror sits in a local directory under your user account. The AI agent (Claude, ChatGPT, Codex) only sees what the CLI or MCP server returns - typically the result of a query, not raw bulk data. Credentials are read from your environment or your agent's config; they're never bundled into this repo or transmitted to MSP Skills servers (there are none). The only paths that move data anywhere else are ones you switch on and point at a URL of your own: --deliver webhook:<url>, a feedback endpoint you set, and the --transport http MCP listener on the connectors that have it.

Does this work with Codex, Cursor, Windsurf, Cline, Copilot, or Gemini?

Yes - all of them. Each speaks MCP (some natively, some via an extension or marketplace). The cross-tool table at the top of this README links each one's install path. The pattern is the same: install the MSP Skills binary, point your AI tool at it, authenticate. Tool-specific gotchas (Copilot uses servers in mcp.json not mcpServers, Cline needs an npx workaround on Windows, etc.) are documented in docs/which-agent.md.

Do I need to know how to code?

No. The recommended install path is to paste one sentence into Claude Code or Codex - your agent reads SKILL.md and does the install. The fallback is a one-line installer per OS (bash or PowerShell). Neither path requires writing code, editing JSON in a text editor, or installing Node, Python, Docker, or a database. You will need to enter API credentials your PSA or backup tool gives you.

Will this hit my vendor's API rate limits?

Almost never. Each connector syncs your data into a local SQLite mirror once, then incrementally; subsequent questions (triage, SLA breaches, client cards, cross-client analytics) run against the local mirror, not the live API. The big-batch QBR queries that get you 429'd with API-passthrough tools become a single SQL join here.

How is this different from my vendor's built-in AI?

Vendor-native AI is great for ticket-by-ticket work - rewriting replies, summarizing one ticket, classifying sentiment. MSP Skills is the MSP-owner-on-the-couch-with-Claude layer: cross-client analytics, ad-hoc questions across thousands of tickets, multi-system queries that join your PSA with your backup tool. The two complement each other; you don't have to choose.

Can I run this on Windows?

Yes. The PowerShell installer in "Install in 60 seconds" above is the same install path as macOS / Linux, just packaged for PowerShell. The CLI and MCP binaries are native Windows builds. Cline users on Windows may need a small npx workaround documented in docs/which-agent.md.

What does it cost?

The Skills, the CLI binaries, and the MCP servers are free. Apache-2.0 licensed - free to use commercially, free to fork. Servosity does not charge for API access required to run the Servosity skill. Other PSA, RMM, and backup vendors set their own API-access terms. You pay only for whichever AI agent you use (Claude, ChatGPT, Codex, etc.), and those are billed by your AI provider, not by us.

Can I try it on one client first?

Yes. Every command takes a client / company filter (e.g. halopsa-cli client card "Acme Corp", servosity-cli company show 4421). Read-tier commands change nothing; you can try them against your live system safely. For writes, each skill's governance.md tags every command with a recommended agent policy - preview with --dry-run and approve before the real thing. The safe starting move is a read-only triage against one client, see the output, then widen scope.

What if my AI doesn't speak MCP?

If your AI doesn't yet support MCP and isn't Claude Code / Codex CLI (which read SKILL.md directly), MSP Skills won't fit yet. Every connector's CLI binary still works standalone in a shell - you can pipe its output into anything. As more AI tools add MCP (the protocol is moving fast in 2026), they'll work with MSP Skills automatically without anything changing on our side.

Built and tested live with MSPs

These skills are built and tested with real MSPs running them against their own production systems, live, in our free weekly Build Sessions (Thursdays). An MSP brings a system we have not covered - your PSA, RMM, backup product, or security tool - and we co-build the Claude Code Skill and MCP server live. You watch, you ask, you walk away with a working integration, and every shipped Skill lands here the day it merges.

RSVP for the next one at compoundingteams.com/build-sessions.

Roadmap

We co-build the next skills live with MSPs in the weekly Build Session. The targets the MSP community asks for most, in demand order:

NinjaOne fleet hygiene (the fastest-growing RMM; silent-failure detector)
Autotask PSA (ConnectWise PSA and HaloPSA shipped - Autotask completes the big three)
IT Glue / Hudu (RMM ticket-to-doc: resolution to documentation)
M365 governance / Copilot data-exposure pre-check
Datto RMM, Kaseya VSA, Atera, Syncro

Want one of these next? Bring the system to a Build Session (above) or open an issue.

Don't see the system you need?

Easiest path - tell your AI. Paste this into Claude Code, Codex, Claude Desktop, or ChatGPT:

Open an issue on https://github.com/servosity/msp-skills using the skill-request template. The system I want is [YOUR SYSTEM NAME] - my one question for the AI would be "[YOUR QUESTION]", I'm on [Mac or Windows], and my MSP has about [N] techs. Submit it.

Your AI fills the form and posts the issue. Done. (You'll need to be signed in to GitHub in your browser or have a GitHub CLI token where your AI can see it.)

Don't have an AI set up yet? Open the issue directly: Submit a skill request →. First time filing a GitHub issue? See docs/requesting-a-skill.md for a 90-second walkthrough.

More votes (👍 reactions on an issue) move a system up the roadmap. Share with one MSP friend who'd want the same skill.

Contribute a Skill or MCP

If your MSP uses a system we have not covered, send a PR. We co-build alongside contributors in Build Sessions when that is easier than going it alone.

A skill PR includes: SKILL.md (with vendor frontmatter), a README.md with the non-affiliation banner, install.sh + install.ps1, mcp-install.md if it ships an MCP server, and ideally pain-point.md + governance.md. CI enforces the contract (DCO sign-off, frontmatter schema, required files, no secrets, no personal paths). See CONTRIBUTING.md for the full checklist and the non-affiliation banner template.

About Compounding Teams

MSPs are the channel that brings AI to small business. The durable moat is the Compounding Teams methodology for running an MSP where every interaction with a tool, a customer, or a system makes the next one better. Loops close, feedback returns to the source, work compounds instead of evaporating. msp-skills is the part of that methodology you can install: the executable layer that lets your AI agent operate alongside your team in the same systems, with the same context, every day.

Skill - a markdown file (and a binary it drives) that tells a Claude Code / Codex agent how to operate a specific tool. Think of it as a recipe card the AI reads on the fly.
MCP - Model Context Protocol. The open standard that lets AI apps (Claude Desktop, ChatGPT, Cursor, Windsurf, etc.) call tools on a separate server (yours).
MCP server - the small program on your machine that exposes the tools. Every MSP Skills connector ships one (e.g. halopsa-mcp, servosity-mcp).
PSA - Professional Services Automation. The system MSPs use for tickets, contracts, time, billing. HaloPSA, ConnectWise, Autotask are PSAs.
BCDR / Backup and DR - Business Continuity and Disaster Recovery. Servosity is a BCDR vendor.
Cross-client analytics - questions that span multiple clients ("how many backup failures across all 47 clients last quarter") rather than one ("show me ticket #4421").

Standards. Conforms to the open Agent Skills spec (Anthropic, Dec 2025; 40+ agents). MCP-compatible - works with any MCP-capable agent including Hermes and OpenClaw, with metadata.openclaw frontmatter pre-wired so openclaw skills install works on every skill.

Built by Servosity. Maintained by Damien Stevens. Apache-2.0 licensed. See TRADEMARKS.md for vendor non-affiliation and SECURITY.md to report a vulnerability. Methodology: Compounding Teams. Generated CLIs and MCP servers built with CLI Printing Press.