NinjaOne MCP

NinjaOne + AI - for Claude, the ChatGPT desktop app, GitHub Copilot, Gemini CLI, and any agent that speaks MCP

Unofficial. Community-built Claude Code Skill and MCP server for the NinjaOne API. Not affiliated with, endorsed by, or sponsored by NinjaOne, LLC.

[NinjaOne demo - animated preview]

_{▶ Watch the 30-second demo - demo data is simulated; every command shown exists in the real CLI.}

Comparing backup vendors? One of our MSP partners told us, "My guys now spend a tenth of the time on backups." Fixing is included in every Servosity co-managed backup plan, and our engineers tell you what they did. See how co-managed backup works

Every NinjaOne report, plus a local store that answers fleet-wide questions no single API call can: patch compliance, backup gaps, AV blast-radius, health, drift. Works with the AI you already use - ChatGPT (desktop app), Claude Desktop, Codex, Claude Code, Claude Cowork, and GitHub Copilot - plus Gemini CLI. Free, open source, runs on your laptop. Built for MSP owners. No code required.

Works with your agent

The six agents MSP owners actually use (self-serve, works today):

The ChatGPT desktop app runs ninjaone-mcp locally and shares MCP configuration with Codex (OpenAI). ChatGPT on the web needs a remote server, which msp-skills does not support yet. If your team works there, a hosted gateway is the better pick; check that your AI app is on the gateway's setup list. Setup steps: mcp-install.md.

Also for the Microsoft and Google stacks

Big install base, but an honest heads-up: Gemini CLI runs the local binary you just installed, while Microsoft 365 Copilot and the Gemini app need a remote server, which msp-skills does not support yet.

Skill-native agents (also covered): Hermes and OpenClaw read this skill's SKILL.md directly and speak MCP - see their install sections below. Also works with Cursor, Windsurf, Cline, Continue.dev, and Zed via MCP. Full per-tool wire-up: docs/which-agent.md.

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

Install in 60 seconds

Fastest for Claude Desktop - one-click .mcpb

Claude Desktop bundle: the .mcpb launches on macOS (Intel and Apple Silicon), Windows x64 and Linux x64. Every tool shells out to the companion ninjaone-cli. Releases cut from 2026-09-18 on ship that CLI inside the bundle; older bundles contain only the MCP server, so if yours lacks the companion, run the Path A or Path B installer below first (or set NINJAONE_CLI_PATH to an existing binary). Details: #331.

Download NinjaOne MCP (.mcpb) - then open Claude Desktop > Settings > Extensions and select the file. One click, no JSON, no shell. (Browse every NinjaOne release on the releases page.)

Prefer the Claude Code plugin? Add the marketplace once, then install - works immediately, no directory listing required:

/plugin marketplace add Servosity/msp-skills/plugin install ninjaone@msp-skills

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

Copy this into Claude Code, Codex CLI, or Claude Cowork:

Install the NinjaOne 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/ninjaone/install.sh). If it uses Windows PowerShell, run iwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/ninjaone/install.ps1 | iex. Then authenticate per the README and run ninjaone-cli --help to explore.

The same prompt works in any agent that can run shell.

Path B - run the installer yourself

Windows (PowerShell):

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

macOS / Linux:

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

The installer drops both ninjaone-cli (the CLI) and ninjaone-mcp (the MCP server) into your user bin path. Claude Code, Codex, and Cowork discover the Skill via SKILL.md in this directory.

Verify:

ninjaone-cli --version

Upgrade to the latest version

The installer always fetches the current release - re-run it to upgrade:

macOS / Linux:

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

Windows (PowerShell):

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

Claude Desktop .mcpb users: download the latest .mcpb (top of this section) and re-select it in Settings > Extensions. Claude Code plugin users: /plugin update ninjaone@msp-skills.

Add to Claude Desktop, the ChatGPT desktop app, GitHub Copilot, Gemini CLI, or another MCP client

After the installer runs, see mcp-install.md and docs/which-agent.md for the per-agent wire-up - one section per agent, including the GitHub Copilot servers key and the ChatGPT desktop app. Claude Desktop's Settings > Extensions panel is the simplest path; the MCP config block (for users who prefer editing JSON) is documented in mcp-install.md.

Install for Hermes

From the Hermes CLI:

hermes skills install servosity/msp-skills/skills/ninjaone --force

Inside a Hermes chat session:

/skills install servosity/msp-skills/skills/ninjaone --force

Hermes speaks MCP natively, so it can also use the ninjaone-mcp server directly - same install path, same env vars.

Install for OpenClaw

Tell your OpenClaw agent (copy this):

Install the ninjaone skill from https://github.com/servosity/msp-skills/tree/main/skills/ninjaone. The skill defines how its required CLI (ninjaone-cli) can be installed via the openclaw: frontmatter block.

OpenClaw isn't generally available yet; the frontmatter wiring is pre-shipped and will activate the moment OpenClaw launches.

Authenticate

Set the credentials the CLI needs (from your NinjaOne portal):

NINJAONE_CLIENT_ID=<value> NINJAONE_CLIENT_SECRET=<value> NINJAONE_OAUTH_SCOPE=<value> ninjaone-cli doctor

doctor confirms the credentials work before you run anything that touches data. It exits 0 even when the credential is rejected, so scripts should add --fail-on error.

What this skill does

Full command reference: guide.md. For the AI-agent operating contract (--agent, --dry-run, when to confirm before mutating), see AGENTS.md.

What makes this different

Most NinjaOne integrations and MCP servers proxy each question into a live API call. That's fine for one device. It dies at scale, when you're asking "which of my 40 client organizations are below 95% patched, and which endpoints across all of them have no backup" - a question the API only answers as per-device rows you have to fetch, cache, and total yourself.

This skill syncs NinjaOne into a local SQLite mirror with full-text search. Aggregate questions become one local SQL join: instant, offline, and the AI sees the answer, not the raw data. Compound commands like patch-compliance, backup-coverage, fleet-health, and drift join devices against the organization map, the patch and backup reports, and the previous snapshot - cross-fleet rollups a stateless API wrapper can't do.

The pain this closes

NinjaOne is one of the most-loved RMMs for real-time, per-device work. The recurring owner complaint is the layer above one device: reporting and the cross-client rollup. Independent reviews note NinjaOne's built-in reports are "not consistently executive-ready" and that client-facing reporting often needs a third-party BI overlay - a gap still open in 2026 - alongside the lack of a single unified multi-tenant view (Flamingo, NinjaOne Review and NinjaOne vs Intune, 2026).

So the questions you ask every week aren't one click - they're a per-org report run N times and re-totaled by hand. This skill makes them one command:

See pain-point.md for the longer narrative.

Frequently asked questions

How do I connect Claude to NinjaOne?

Install this free NinjaOne MCP server, give it the client ID and secret of a NinjaOne API app (create one under Administration > Apps > API), and Claude can answer questions about your NinjaOne tenant in plain English. In Claude Desktop, select the one-click .mcpb under Settings > Extensions; in Claude Code, run /plugin install ninjaone@msp-skills; for any other agent, run the installer and follow the agent setup guide. Every path is in Install in 60 seconds. If you sign in to NinjaOne somewhere other than app.ninjarmm.com, also set NINJAONE_BASE_URL and NINJAONE_TOKEN_URL (see the regions question below). Run ninjaone-cli sync once (or ask Claude to sync NinjaOne) before your first fleet-wide question.

Other ways to connect the two include community MCP servers such as WYRE's ninjaone-mcp and Lungshot's NinjaOneMCP, and hosted connector services such as Truto and MCPBundles. This one keeps a local SQLite copy of your estate, so fleet-wide questions are answered from the local copy without calling the API again, and it ships as prebuilt binaries (the MCP server and its companion CLI), so running it outside Claude Desktop needs no Node.js or Docker. An MSP has also confirmed it against a production NinjaOne tenant (receipt).

Does this work with ChatGPT?

Yes, in the ChatGPT desktop app. It runs MCP servers locally (STDIO), the way ninjaone-mcp runs, and shares MCP configuration with Codex (OpenAI): add ninjaone-mcp under Settings > MCP servers as a STDIO server, or add it once to Codex's ~/.codex/config.toml. ChatGPT on the web is not supported by msp-skills yet: it needs a remote server. If your team works there, a hosted gateway is the better pick; check that your AI app is on the gateway's setup list. Setup steps: mcp-install.md.

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

Yes - all of them speak MCP. Cross-tool install commands are in the matrix above and the deep-dive in docs/which-agent.md.

Do I need to know how to code?

No. The recommended install 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. You'll enter your NinjaOne credentials once.

Is my NinjaOne data safe?

Your data stays on your machine. The CLI and MCP server are local binaries. The SQLite mirror sits in a directory under your user account. The AI agent only sees what the CLI returns - typically a query result, not raw bulk data. Credentials are read from your environment or your agent's config; never bundled into this repo or transmitted anywhere by MSP Skills.

Does it work with the US, EU, and other NinjaOne regions?

Yes. The US host (https://app.ninjarmm.com) is the default. For another region, set NINJAONE_BASE_URL (for example https://eu.ninjarmm.com) and NINJAONE_TOKEN_URL (for example https://eu.ninjarmm.com/ws/oauth/token), then run ninjaone-cli doctor to confirm the credentials reach your instance.

Will this hit my NinjaOne API rate limits?

The local mirror exists so reads stop hitting the API. After the first sync, the fleet views (patch-compliance, backup-coverage, av-sweep, fleet-health, stale-devices, os-eol, software-audit, drift) run against local SQLite with zero API calls. Live calls respect a --rate-limit throttle, and sync is incremental and resumable - it only fetches what changed and treats resources your token can't reach as warnings, not failures.

Do I need to be a NinjaOne partner or buy the reporting add-on?

No. You create an API app yourself under Administration > Apps > API with an OAuth2 client_id and client_secret. The fleet rollups are computed locally from whatever your token can already read - no reporting add-on, data warehouse, or partner tier required.

Can it change things in NinjaOne, or is it read-only?

The headline fleet views are read-only. The CLI also wraps NinjaOne's write surface (for example updating an organization, creating a ticket, running a script, rebooting a device) and a smaller destructive tier (deletes). Preview any write with --dry-run, keep a human in the loop, and scope the API token to only what your workflow needs. See governance.md.

What does it cost?

Free. Apache-2.0 licensed. You pay only for whichever AI agent you use (Claude, ChatGPT, Codex, etc.), and that's billed by your AI provider, not by us.

Safety model

The strongest control is the scope you grant the NinjaOne credentials - the CLI can only do what the credentials are permitted to do. Full details, including how to lock it down, are in governance.md.

Status

Live-verified. Confirmed by @Xenith-B (MSP) against their own production tenant (receipt). More MSPs run it live in our weekly Build Sessions. RSVP at compoundingteams.com/build-sessions.

Standards. Conforms to the open Agent Skills spec (Anthropic, Dec 2025; 40+ agents). MCP-compatible - works with any MCP-capable agent including Hermes. OpenClaw-ready (frontmatter pre-wired, awaiting OpenClaw launch).

Maintained by Servosity. Apache-2.0 licensed. Built with CLI Printing Press. Last updated: 2026-06-05.