Microsoft Graph logo

Microsoft Graph

Organization
Servosity
microsoft-graph

The maintained single-binary successor to the retiring mgc - every MSP-relevant Microsoft Graph surface, plus an offline store that finds wasted licenses, privileged-access risks, over-privileged third-party app consents, and stale devices no single API call can. Trigger phrases: `find unused microsoft 365 licenses`, `who has global admin in this tenant`, `audit third-party app consent`, `which apps can read our mail`, `triage microsoft defender alerts`, `list non-compliant intune devices`, `microsoft graph tenant snapshot`, `use microsoft-graph`, `run microsoft-graph`.

Overview

PublisherServosity
Repositorymsp-skills
Skill namemicrosoft-graph
Stars
68
Forks
14
Bundled files
140
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 140 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Servosity on GitHub. Read the source before you install it.

Installation

Install the Microsoft Graph AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Servosity/msp-skills/tree/main/skills/microsoft-graph
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Servosity/msp-skills.git /tmp/msp-skills
mkdir -p .claude/skills
cp -r /tmp/msp-skills/skills/microsoft-graph .claude/skills/microsoft-graph
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Microsoft Graph in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Microsoft Graph on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Microsoft Graph is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Microsoft Graph - Claude Code Skill

Prerequisites: Install the CLI

This skill drives the microsoft-graph-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first:

  1. macOS / Linux:
    bash
    bash <(curl -fsSL https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/microsoft-graph/install.sh)
  2. Windows (PowerShell):
    powershell
    iwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/microsoft-graph/install.ps1 | iex
  3. Verify: microsoft-graph-cli --version
  4. Ensure ~/.local/bin (macOS / Linux) or %LOCALAPPDATA%\Programs\msp-skills (Windows) is on $PATH.

The installer downloads the microsoft-graph-cli and microsoft-graph-mcp binaries into ~/.local/bin (macOS / Linux) or %LOCALAPPDATA%\Programs\msp-skills (Windows). It does not register the skill with your agent and writes no MCP client config - see mcp-install.md for that wire-up.

If --version reports "command not found" after install, the runtime cannot see the binary directory on $PATH. Do not proceed with skill commands until verification succeeds.

Microsoft is retiring the Microsoft Graph CLI (mgc) in August 2026, leaving M365 admins and MSPs without a lightweight, scriptable replacement scoped to the directory, security, licensing, and device core. This is that replacement: one cross-platform Go binary (no .NET or PowerShell runtime), with a local SQLite store that powers cross-entity answers - licenses waste, admins audit, security triage, managed-devices drift, tenant snapshot - that no single Graph endpoint returns.

When to Use This CLI

Reach for this CLI for read-side Microsoft 365 / Entra tenant administration from a terminal, script, or agent: directory lookups (users, groups, roles), licensing and cost questions, security-alert triage, and Intune device-compliance reporting. It is the right tool when you want one cross-platform binary instead of the retiring mgc, the PowerShell Microsoft.Graph module, or the M365 admin portals - and especially when the question spans entities (waste, orphaned licenses, privileged access, compliance drift, tenant posture) that no single Graph call answers. It is read-focused; apart from the explicit import command (a JSONL create path, previewable with --dry-run), it does not create, update, or delete directory objects. The cross-entity analytics commands (licenses waste/orphans/map, admins audit, security triage, managed-devices drift, tenant snapshot, groups risk) read the LOCAL SQLite store - run microsoft-graph-cli pull first to populate it, or they will honestly return empty results with a stderr sync hint.

Anti-triggers

Do not use this CLI for:

  • Do not use this CLI to create, update, or delete directory objects, send mail, or change tenant state - the only write path is the explicit import command (JSONL create, previewable with --dry-run).
  • Do not use the cross-entity analytics commands against a never-synced store and treat empty output as a real answer - run pull first; an unsynced store returns honest empties with a stderr hint.

Unique Capabilities

These capabilities aren't available in any other tool for this API.

License cost intelligence

  • licenses waste - Surfaces every tenant SKU where you are paying for more seats than you use, ranked by unused seats.

    Reach for this to find recoverable M365 license spend across a tenant in one call instead of exporting SKU CSVs from the admin center.

    bash
    microsoft-graph-cli licenses waste --agent
  • licenses orphans - Lists disabled and guest accounts that still hold paid SKUs - licenses you are paying for but nobody is using.

    Use before a license true-up to reclaim seats assigned to disabled or guest identities.

    bash
    microsoft-graph-cli licenses orphans --json
  • licenses map - Lists every user consuming a specific SKU, with account-enabled state and guest flags, so you can plan seat reclamation and reassignment.

    Reach for this when you need to know exactly who holds a given SKU before reclaiming or reassigning seats.

    bash
    microsoft-graph-cli licenses map ENTERPRISEPACK --agent

Security & privileged-access

  • admins audit - Lists every holder of a privileged directory role with the role name, account-enabled state, and guest/disabled risk flags.

    Run this for the monthly privileged-access review - it is the fastest answer to 'who can administer this tenant right now'.

    bash
    microsoft-graph-cli admins audit --agent
  • security triage - Counts the open security alerts created in a recent time window, grouped by severity and detection source.

    Reach for this every morning to answer 'what is new and still open since yesterday' without portal pagination.

    bash
    microsoft-graph-cli security triage --since 24h --agent
  • groups risk - Flags ownerless, empty, and guest-heavy groups across the tenant in one pass.

    Use this for tenant governance reviews when no single Graph filter can surface risky groups.

    bash
    microsoft-graph-cli groups risk --agent

Device & tenant posture

  • managed-devices drift - Flags Intune devices that are non-compliant, unencrypted, or have not checked in within a time window, attributed to their assigned user.

    Use to build the weekly device-compliance ticket queue in one command instead of a portal-to-spreadsheet ETL.

    bash
    microsoft-graph-cli managed-devices drift --days 30 --json
  • tenant snapshot - One agent-readable summary of the tenant: user and guest counts, license waste, admin count, open high-severity alerts, and non-compliant device count.

    Reach for this first when you pick up a tenant - it is the 'where does this tenant stand' answer an MSP needs before drilling in.

    bash
    microsoft-graph-cli tenant snapshot --agent

Command Reference

devices - Entra ID registered/joined device objects

  • microsoft-graph-cli devices get - Get an Entra device by object id
  • microsoft-graph-cli devices list - List Entra-registered devices

directory-roles - Entra ID directory roles (admin roles) and their members

  • microsoft-graph-cli directory-roles get - Get a directory role by object id
  • microsoft-graph-cli directory-roles list - List activated directory roles in the tenant
  • microsoft-graph-cli directory-roles members - List the members assigned to a directory role

groups - Entra ID groups - list, get, members, and owners

  • microsoft-graph-cli groups get - Get a group by object id
  • microsoft-graph-cli groups list - List groups in the tenant
  • microsoft-graph-cli groups members - List a group's members
  • microsoft-graph-cli groups owners - List a group's owners

licenses - Tenant commercial subscriptions (subscribedSkus)

  • microsoft-graph-cli licenses sku - Get a single subscribed SKU by id
  • microsoft-graph-cli licenses skus - List the commercial subscriptions (SKUs) the tenant owns

managed-devices - Intune-managed devices and their compliance posture

  • microsoft-graph-cli managed-devices get - Get an Intune-managed device by id
  • microsoft-graph-cli managed-devices list - List Intune-managed devices (requires an Intune license)

security - Microsoft Defender / Sentinel security alerts and incidents

  • microsoft-graph-cli security alert - Get a security alert by id
  • microsoft-graph-cli security alerts - List security alerts (alerts_v2)
  • microsoft-graph-cli security incident - Get a security incident by id
  • microsoft-graph-cli security incidents - List security incidents

users - Entra ID (Azure AD) users - list, get, mail, and license details

  • microsoft-graph-cli users get - Get a user by object id or userPrincipalName
  • microsoft-graph-cli users licenses - List the SKUs/licenses assigned to a user
  • microsoft-graph-cli users list - List users in the tenant
  • microsoft-graph-cli users me - Get the signed-in user (delegated tokens only; app-only tokens have no /me)
  • microsoft-graph-cli users messages - List a user's mail messages

Finding the right command

When you know what you want to do but not which command does it, ask the CLI directly:

bash
microsoft-graph-cli which "<capability in your own words>"

which resolves a natural-language capability query to the best matching command from this CLI's curated feature index. Exit code 0 means at least one match; exit code 2 means no confident match - fall back to --help or use a narrower query.

Recipes

Find recoverable license spend

bash
microsoft-graph-cli licenses waste --agent

Ranks SKUs by unused paid seats so you can right-size subscriptions at renewal.

Monthly privileged-access review

bash
microsoft-graph-cli admins audit --agent

Lists every directory-role holder with risk flags for guest or disabled admin accounts.

Morning alert triage

bash
microsoft-graph-cli security triage --since 24h --agent

Groups open alerts from the last day by severity and detection source.

Device compliance ticket queue

bash
microsoft-graph-cli managed-devices drift --days 30 --agent

Surfaces non-compliant, unencrypted, or stale-sync Intune devices mapped to their user.

Trim a large user payload to just the fields you need

bash
microsoft-graph-cli users list --top 50 --agent --select id,displayName,userPrincipalName,accountEnabled

Pairs --agent with --select to keep agent context small when a Graph user object would otherwise return dozens of properties.

Auth Setup

Microsoft Graph uses OAuth2 bearer tokens. For unattended MSP use, run auth login --tenant <tenant-id> --client-id <app-id> --client-secret <secret> to mint and cache an app-only token via the client-credentials flow. Alternatively, export a pre-minted token as MICROSOFT_GRAPH_TOKEN (for example from az account get-access-token --scope https://graph.microsoft.com/.default --query accessToken -o tsv or Graph Explorer). Read scopes such as User.Read.All, Directory.Read.All, RoleManagement.Read.Directory, SecurityAlert.Read.All, and DeviceManagementManagedDevices.Read.All must be granted and admin-consented on the app registration.

Run microsoft-graph-cli doctor to verify setup.

Agent Mode

Add --agent to any command. Expands to: --json --compact --no-input --no-color --yes.

  • Pipeable - JSON on stdout, errors on stderr

  • Filterable - --select keeps a subset of fields. Dotted paths descend into nested structures; arrays traverse element-wise. Critical for keeping context small on verbose APIs:

    bash
    microsoft-graph-cli devices list --agent --select id,name,status
  • Previewable - --dry-run shows the request without sending

  • Offline-friendly - sync/search commands can use the local SQLite store when available

  • Non-interactive - never prompts, every input is a flag

  • Read-only - do not use this CLI for create, update, delete, publish, comment, upvote, invite, order, send, or other mutating requests

Response envelope

Commands that read from the local store or the API wrap output in a provenance envelope:

json
{
  "meta": {"source": "live" | "local", "synced_at": "...", "reason": "..."},
  "results": <data>
}

Parse .results for data and .meta.source to know whether it's live or local. A human-readable N results (live) summary is printed to stderr only when stdout is a terminal AND no machine-format flag (--json, --csv, --compact, --quiet, --plain, --select) is set - piped/agent consumers and explicit-format runs get pure JSON on stdout.

Agent Feedback

When you (or the agent) notice something off about this CLI, record it:

microsoft-graph-cli feedback "the --since flag is inclusive but docs say exclusive"
microsoft-graph-cli feedback --stdin < notes.txt
microsoft-graph-cli feedback list --json --limit 10

Entries are stored locally at ~/.local/share/microsoft-graph-cli/feedback.jsonl. They are never POSTed unless MICROSOFT_GRAPH_FEEDBACK_ENDPOINT is set AND either --send is passed or MICROSOFT_GRAPH_FEEDBACK_AUTO_SEND=true. Default behavior is local-only.

Write what surprised you, not a bug report. Short, specific, one line: that is the part that compounds.

Output Delivery

Every command accepts --deliver <sink>. The output goes to the named sink in addition to (or instead of) stdout, so agents can route command results without hand-piping. Three sinks are supported:

SinkEffect
stdoutDefault; write to stdout only
file:<path>Atomically write output to <path> (tmp + rename)
webhook:<url>POST the output body to the URL (application/json or application/x-ndjson when --compact)

Unknown schemes are refused with a structured error naming the supported set. Webhook failures return non-zero and log the URL + HTTP status on stderr.

Named Profiles

A profile is a saved set of flag values, reused across invocations. Use it when a scheduled agent calls the same command every run with the same configuration - HeyGen's "Beacon" pattern.

microsoft-graph-cli profile save briefing --json
microsoft-graph-cli --profile briefing devices list
microsoft-graph-cli profile list --json
microsoft-graph-cli profile show briefing
microsoft-graph-cli profile delete briefing --yes

Explicit flags always win over profile values; profile values win over defaults. agent-context lists all available profiles under available_profiles so introspecting agents discover them at runtime.

Exit Codes

CodeMeaning
0Success
2Usage error (wrong arguments)
3Resource not found
4Authentication required
5API error (upstream issue)
7Rate limited (wait and retry)
10Config error

Argument Parsing

Parse $ARGUMENTS:

  1. Empty, help, or --help → show microsoft-graph-cli --help output
  2. Starts with install → ends with mcp → MCP installation; otherwise → see Prerequisites above
  3. Anything else → Direct Use (execute as CLI command with --agent)

MCP Server Installation

  1. Install the MCP binary (run the install script from the Prerequisites section, or see mcp-install.md for per-agent wire-up).
  2. Register with Claude Code:
    bash
    claude mcp add microsoft-graph-mcp -- microsoft-graph-mcp
  3. Verify: claude mcp list

Direct Use

  1. Check if installed: which microsoft-graph-cli If not found, offer to install (see Prerequisites at the top of this skill).
  2. Match the user query to the best command from the Unique Capabilities and Command Reference above.
  3. Execute with the --agent flag:
    bash
    microsoft-graph-cli <command> [subcommand] [args] --agent
  4. If ambiguous, drill into subcommand help: microsoft-graph-cli <command> --help.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

and 80 more files.

Frequently asked questions

What does the Microsoft Graph AI skill do?

The maintained single-binary successor to the retiring mgc - every MSP-relevant Microsoft Graph surface, plus an offline store that finds wasted licenses, privileged-access risks, over-privileged third-party app consents, and stale devices no single API call can. Trigger phrases: `find unused microsoft 365 licenses`, `who has global admin in this tenant`, `audit third-party app consent`, `which apps can read our mail`, `triage microsoft defender alerts`, `list non-compliant intune devices`, `microsoft graph tenant snapshot`, `use microsoft-graph`, `run microsoft-graph`.

Why use Microsoft Graph on TypingMind?

Because you install it once and use it with any model. Microsoft Graph is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Microsoft Graph in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Servosity/msp-skills/tree/main/skills/microsoft-graph. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Microsoft Graph?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Microsoft Graph?

As many as you like. As long as a model supports skills, you can use Microsoft Graph with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Microsoft Graph AI skill free?

Yes. It is published on GitHub by Servosity under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇