mcp-ninjaone
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-ninjaone Show me all active alerts and which devices are currently offline"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-ninjaone
A Model Context Protocol (MCP) server for NinjaOne (formerly NinjaRMM), providing AI assistants with full access to remote monitoring and management through the NinjaOne REST API v2.
Features
19 tools across five categories:
Device Management
Tool | Description |
| List all managed devices with online status, OS, organization, and last contact |
| Get detailed device info including hardware, agent version, and network details |
| Get recent activity log for a device (alerts, scripts, status changes) |
| View pending, installed, and failed OS patches for a device |
| List all installed software on a device |
| Get CPU/processor details for a device |
| Get disk/storage info including capacity and free space |
Organizations
Tool | Description |
| List all organizations (clients/customers) with ID, name, and node count |
| Get detailed organization info including contacts, tags, and policy assignments |
| List all devices belonging to a specific organization |
| Get configured locations for an organization |
| Get policy assignments for an organization |
Alerts & Conditions
Tool | Description |
| List active alerts across all devices, filterable by severity |
| List all active alerts for a specific device |
| Reset (acknowledge and clear) an active alert by its UID |
| List all configured alert trigger conditions |
Maintenance Windows
Tool | Description |
| List all scheduled maintenance windows |
| Create a maintenance window for a device to suppress alerts |
| Cancel an active maintenance window to re-enable alerting |
Jobs & Automation
Tool | Description |
| List currently running jobs across all devices |
| Get all jobs (running, completed, failed) for a specific device |
| Execute a saved script on a device |
Related MCP server: ninjaone-mcp
Installation
git clone git@github.com:fredriksknese/mcp-ninjaone.git
cd mcp-ninjaone
npm install
npm run buildConfiguration
The server is configured via environment variables:
Variable | Required | Description |
| Yes | OAuth2 client ID from NinjaOne API credentials |
| Yes | OAuth2 client secret from NinjaOne API credentials |
| Yes | NinjaOne instance hostname (see table below) |
Instance Hostnames
Region | Hostname |
US |
|
EU |
|
Oceania |
|
Canada |
|
Creating API Credentials
Log in to your NinjaOne instance
Navigate to Administration > Apps > API
Click Add to create a new API application
Select Client Credentials as the authorization flow
Grant the required scopes:
monitoring,management,control,offline_accessCopy the Client ID and Client Secret
Usage with Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"ninjaone": {
"command": "node",
"args": ["/absolute/path/to/mcp-ninjaone/dist/index.js"],
"env": {
"NINJAONE_CLIENT_ID": "your-client-id",
"NINJAONE_CLIENT_SECRET": "your-client-secret",
"NINJAONE_INSTANCE": "app.ninjarmm.com"
}
}
}
}Usage with Claude Code
Add to your Claude Code MCP settings:
claude mcp add ninjaone -- node /absolute/path/to/mcp-ninjaone/dist/index.jsSet the required environment variables before running, or configure them in your MCP settings.
Example Prompts
Once connected, you can ask your AI assistant things like:
"Show me all devices that are currently offline"
"What active alerts do we have across all organizations?"
"Put device 1234 into maintenance mode for the next 2 hours"
"List all devices for the Acme Corp organization"
"What software is installed on device 5678?"
"Show me recent activity for device 1234"
"Run the cleanup script on device 9012"
"What jobs are currently running across all devices?"
"Reset all minor alerts for device 1234"
"What patches are pending on device 5678?"
Development
npm run dev # Run with tsx (auto-reloads)
npm run build # Compile TypeScript to dist/
npm start # Run compiled outputArchitecture
src/
├── index.ts # Entry point — creates MCP server + STDIO transport
├── ninjaone-client.ts # HTTP client with OAuth2 client credentials flow
└── tools/
├── devices.ts # Device management and inventory (7 tools)
├── organizations.ts # Organization/client management (5 tools)
├── alerts.ts # Alert monitoring and acknowledgement (4 tools)
├── maintenance.ts # Maintenance window management (3 tools)
└── jobs.ts # Job execution and monitoring (3 tools)The client handles OAuth2 token lifecycle automatically — tokens are fetched on first use and refreshed when they expire (typically after 1 hour).
Requirements
Node.js 18+
NinjaOne account with API access enabled
License
SEE LICENSE IN LICENSE
Available Tools
22 toolscancel_device_maintenanceA
Cancel an active maintenance window for a device, immediately re-enabling alerting.
Inputs: device_id (required).
create_maintenance_windowB
Create a maintenance window for a device to suppress alerts during planned maintenance. The window disables alerting for the specified duration.
Inputs: device_id (required), start (required), end (required), disable_alerts.
get_deviceA
Get detailed information about a specific device by its ID, including hardware, OS, agent version, and network details.
Inputs: device_id (required).
get_device_activitiesA
Get recent activity log for a specific device. Shows events such as alerts triggered, scripts run, and status changes.
Inputs: device_id (required), page_size, after, activity_type.
get_device_disksA
Get disk/storage information for a specific device, including capacity and free space.
Inputs: device_id (required).
get_device_jobsB
Get all jobs (running, completed, and failed) for a specific device.
Inputs: device_id (required), job_type.
get_device_os_patch_statusA
Get the OS patch status for a specific device, showing pending, installed, and failed patches.
Inputs: device_id (required).
get_device_processor_infoB
Get CPU/processor information for a specific device.
Inputs: device_id (required).
get_device_softwareB
Get the list of installed software on a specific device.
Inputs: device_id (required).
get_organizationA
Get detailed information about a specific organization by its ID, including contact info, tags, and policy assignments.
Inputs: organization_id (required).
get_organization_locationsA
Get the locations configured for a specific organization.
Inputs: organization_id (required).
get_organization_policiesA
Get the policy assignments for a specific organization.
Inputs: organization_id (required).
list_alert_conditionsB
List all configured alert conditions (triggers) in NinjaOne.
Inputs: page_size.
list_alertsB
List active alerts and conditions across all devices in NinjaOne. Returns alert UID, severity, message, device, and trigger time.
Inputs: severity, device_filter, page_size, after.
list_device_alertsB
List all active alerts for a specific device.
Inputs: device_id (required).
list_devicesB
List all devices managed by NinjaOne. Returns device name, OS, online status, organization, and last contact time.
Inputs: page_size, after, organization_id.
list_maintenance_windowsA
List all scheduled maintenance windows across organizations and devices. Maintenance windows suppress alerts during planned work.
Inputs: page_size.
list_organization_devicesC
List all devices belonging to a specific organization.
Inputs: organization_id (required).
list_organizationsB
List all organizations (clients/customers) in NinjaOne. Returns organization ID, name, description, and node count.
Inputs: page_size, after.
list_running_jobsA
List currently running jobs across all devices. Jobs include scripting tasks, patch installations, and other automated operations.
Inputs: device_filter, job_type, page_size.
reset_alertA
Reset (acknowledge and clear) an active alert by its UID. Use list_alerts or list_device_alerts to find the alert UID.
Inputs: alert_uid (required).
run_script_on_deviceA
Execute a saved script on a specific device. The script must already exist in NinjaOne's script library.
Inputs: device_id (required), script_id (required), run_as, parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 22 tools
Each tool targets a distinct resource and action. Tools like list_alerts and list_device_alerts are clearly differentiated by scope (global vs. per-device). No overlapping purposes.
All tools follow a consistent verb_noun pattern (e.g., get_device, list_organizations, create_maintenance_window). No mixing of styles like camelCase or inconsistent verbs.
22 tools is slightly above the typical well-scoped range (3-15) but justified given the breadth of RMM functionality covered (devices, alerts, maintenance, organizations, scripts).
Covers many key operations for device and alert management, but lacks full CRUD for devices, organizations, and scripts (e.g., no create_device, update_organization, or delete_script). Notable gaps in lifecycle coverage.
Maintenance
Related MCP Connectors
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
Hosted MCP servers for MSP tools: ConnectWise, NinjaOne, Microsoft 365, SentinelOne, Pax8 and more.
One MCP server for the services your AI needs: memory, files, Microsoft 365, kanban and more.
AI-powered incident management and server monitoring via MCP.
Related MCP Servers
- FlicenseCqualityDmaintenanceMCP server providing 75 tools for querying devices, managing alerts, running scripts, creating tickets, and more via the NinjaOne RMM platform.96-
- AlicenseNot gradedqualityBmaintenanceAn MCP server for the NinjaOne RMM platform, enabling tools to manage devices, organizations, alerts, jobs, and policies through NinjaOne's API.32Apache 2.0
- AlicenseNot gradedqualityBmaintenanceMCP server for Kaseya VSA — endpoints, patches, procedures, alarms, and tickets. Enables AI assistants to manage and monitor devices via the Kaseya VSA RMM platform.Apache 2.0
- AlicenseBqualityBmaintenanceMCP server that gives AI assistants read-only access to TacticalRMM fleet data (agents, checks, alerts, services, processes, etc.) and, with explicit approval, lets them run commands on managed machines.2048 PyPI4AGPL 3.0