Connectwise Automate logo

Connectwise Automate

Organization
Servosity
connectwise-automate

Use when the user asks to check ConnectWise Automate fleet health, find stale or offline agents, report patch compliance by client, triage open alerts across clients, inventory end-of-life OSes, or see what changed overnight across an RMM fleet. Syncs your whole Automate server into a local SQLite mirror so it answers cross-client questions the per-server console can't. Trigger phrases: `connectwise automate fleet health`, `stale automate agents`, `automate patch compliance by client`, `triage automate alerts`, `use connectwise automate`, `run connectwise-automate-cli`.

Overview

PublisherServosity
Repositorymsp-skills
Skill nameconnectwise-automate
Stars
68
Forks
14
Bundled files
150
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.

  • 150 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 Connectwise Automate 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/connectwise-automate
  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/connectwise-automate .claude/skills/connectwise-automate
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Connectwise Automate 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 Connectwise Automate 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 Connectwise Automate 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.

ConnectWise Automate Claude Code Skill

Prerequisites: Install the CLI

This skill drives the connectwise-automate-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/connectwise-automate/install.sh)
  2. Windows (PowerShell):
    powershell
    iwr -useb https://raw.githubusercontent.com/servosity/msp-skills/main/skills/connectwise-automate/install.ps1 | iex
  3. Verify: connectwise-automate-cli --version
  4. Ensure ~/.local/bin (macOS / Linux) or %LOCALAPPDATA%\Programs\msp-skills (Windows) is on $PATH.

If --version reports "command not found" after install, the install step did not put the binary on $PATH. Do not proceed with skill commands until verification succeeds.

ConnectWise Automate's value is locked behind a per-server console built for one-endpoint-at-a-time work. This CLI syncs your whole fleet - computers, clients, locations, alerts, and patch history - into local SQLite, then answers the questions MSPs actually ask across clients: where the offline agents are (stale-agents), who's behind on patches (patch-compliance), and what changed overnight (since). Everything is offline, scriptable, and built for AI agents.

Unique Capabilities

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

Cross-client roll-ups the per-server UI can't do

  • fleet-health - See every agent across every client in one roll-up: online/offline, last-contact age, and open-alert count, grouped by client.

    Reach for this when an agent needs the whole-fleet posture in one shot instead of paging the Computers endpoint client by client.

    bash
    connectwise-automate-cli fleet-health --agent
  • stale-agents - List computers not seen in N days, grouped by client - the offline agents bleeding license and hiding risk.

    Use before license true-ups or security reviews to find agents that stopped checking in.

    bash
    connectwise-automate-cli stale-agents --days 30 --agent
  • patch-compliance - Per-client patch posture from synced patch history joined to computers - worst offenders first.

    Pull this before a QBR or a security conversation to name the clients that are behind.

    bash
    connectwise-automate-cli patch-compliance --agent
  • client-rollup - One-line-per-client snapshot: computers, locations, offline agents, and open alerts - built for the client review.

    The fastest way to brief on a client's whole environment without clicking through the console.

    bash
    connectwise-automate-cli client-rollup --agent

Triage and inventory

  • alert-triage - Open alerts across every client, ranked by priority and joined to computer → location → client, with duplicates collapsed.

    Start the morning here to see what actually needs a human across the whole book of business.

    bash
    connectwise-automate-cli alert-triage --min-priority 3 --agent
  • os-inventory - Fleet-wide operating-system distribution with end-of-life OSes (Windows 7, Server 2008/2012) flagged for upgrade planning.

    Use for security and hardware-refresh planning when you need the EOL exposure across every client at once.

    bash
    connectwise-automate-cli os-inventory --eol-only --agent
  • since - Fleet activity in the last N hours from the records' own timestamps: alerts created, agents that checked in, and patches installed.

    Run first thing to catch overnight activity across the fleet without paging each endpoint.

    bash
    connectwise-automate-cli since --hours 24 --agent

Recipes

Morning triage across all clients

bash
connectwise-automate-cli alert-triage --min-priority 3 --agent --select client,computer,priority,message

Narrows the alert payload to the four fields that matter so an agent doesn't burn context on the full alert objects.

Find offline agents for a license true-up

bash
connectwise-automate-cli stale-agents --days 45 --agent

Lists computers not seen in 45 days, grouped by client, straight from the local store.

Patch posture for a QBR

bash
connectwise-automate-cli patch-compliance --agent

Per-client patch percentages, worst first, ready to paste into a client review.

Filter live computers without syncing

bash
connectwise-automate-cli computers list --condition "Status='Offline'" --order-by "LastContact asc" --agent

Uses Automate's own condition/orderby query against the live API when you don't want a full sync.

Command Reference

alerts - Open monitor alerts across the fleet

  • connectwise-automate-cli alerts get - Get a single alert by Id
  • connectwise-automate-cli alerts list - List open alerts across all computers

apitoken - Mint and refresh API bearer tokens

  • connectwise-automate-cli apitoken mint - Mint a bearer token from username + password (needs CONNECTWISE_AUTOMATE_SERVER + clientId header)
  • connectwise-automate-cli apitoken refresh - Refresh an existing (still-valid) bearer token

clients - Clients (companies / customers) in Automate

  • connectwise-automate-cli clients get - Get a single client by Id
  • connectwise-automate-cli clients list - List all clients

commands - Available commands that can be executed on agents

  • connectwise-automate-cli commands get - Get a single command by Id
  • connectwise-automate-cli commands list - List all available commands

computers - Managed endpoints (agents) - the core RMM inventory

  • connectwise-automate-cli computers alerts - Open alerts for one computer
  • connectwise-automate-cli computers command-execute - Execute a command on one computer (WRITE - runs a real command on the agent)
  • connectwise-automate-cli computers command-history - Recent command execution history for one computer
  • connectwise-automate-cli computers get - Get a single computer by Id
  • connectwise-automate-cli computers list - List computers across the fleet (paginated, filterable)
  • connectwise-automate-cli computers patching-stats - Patch installation statistics for one computer
  • connectwise-automate-cli computers software - Installed software inventory for one computer

contacts - Client contacts

  • connectwise-automate-cli contacts - List all client contacts

groups - Computer groups (organizational + policy grouping)

  • connectwise-automate-cli groups get - Get a single group by Id
  • connectwise-automate-cli groups list - List all groups

locations - Locations (sites) belonging to clients

  • connectwise-automate-cli locations get - Get a single location by Id
  • connectwise-automate-cli locations list - List all locations

monitors - Monitors and their per-monitor statistics

  • connectwise-automate-cli monitors list - List monitors with their alerting statistics
  • connectwise-automate-cli monitors sensor-checks - List sensor checks

network-devices - Discovered network devices (non-agent)

  • connectwise-automate-cli network-devices - List discovered network devices

patching - Patch history, compliance information, and patch policies

  • connectwise-automate-cli patching approval-policies - Patch approval policies
  • connectwise-automate-cli patching deploy-approved - Deploy all approved patches (WRITE - triggers fleet patch deployment)
  • connectwise-automate-cli patching deploy-security - Deploy all security patches (WRITE - triggers fleet patch deployment)
  • connectwise-automate-cli patching information - Global patch information / catalog status
  • connectwise-automate-cli patching list - Fleet-wide patch installation history
  • connectwise-automate-cli patching microsoft-policies - Microsoft update policies
  • connectwise-automate-cli patching reattempt-failed - Reattempt failed patches (WRITE - retries failed patch installs)
  • connectwise-automate-cli patching thirdparty-policies - Third-party update policies

scripts - Automation scripts and their run state

  • connectwise-automate-cli scripts list - List all scripts
  • connectwise-automate-cli scripts running - List scripts currently running across the fleet
  • connectwise-automate-cli scripts schedules - List scheduled script runs

server - Automate server metadata (used by doctor / health)

  • connectwise-automate-cli server db-time - Current database server time
  • connectwise-automate-cli server info - Server version and metadata

Finding the right command

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

bash
connectwise-automate-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.

Auth Setup

Automate is per-server: set CONNECTWISE_AUTOMATE_SERVER to your host (e.g. company.hostedrmm.com) and CONNECTWISE_AUTOMATE_CLIENT_ID to your registered integration GUID (required for v2020.11+). Mint a bearer token with apitoken mint --username <u> --password <p>, then export CONNECTWISE_AUTOMATE_TOKEN with the returned AccessToken. Tokens are short-lived; refresh with apitoken refresh.

Run connectwise-automate-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
    connectwise-automate-cli alerts 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

  • Explicit retries - use --idempotent only when an already-existing create should count as success

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:

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

Entries are stored locally at ~/.local/share/connectwise-automate-cli/feedback.jsonl. They are never POSTed unless CONNECTWISE_AUTOMATE_FEEDBACK_ENDPOINT is set AND either --send is passed or CONNECTWISE_AUTOMATE_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.

connectwise-automate-cli profile save briefing --json
connectwise-automate-cli --profile briefing alerts list
connectwise-automate-cli profile list --json
connectwise-automate-cli profile show briefing
connectwise-automate-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 connectwise-automate-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

Install the MCP binary (run the install script from the Prerequisites section, or see mcp-install.md for per-agent wire-up), then register it:

bash
claude mcp add connectwise-automate-mcp -- connectwise-automate-mcp

Verify: claude mcp list

Direct Use

  1. Check if installed: which connectwise-automate-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
    connectwise-automate-cli <command> [subcommand] [args] --agent
  4. If ambiguous, drill into subcommand help: connectwise-automate-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 90 more files.

Frequently asked questions

What does the Connectwise Automate AI skill do?

Use when the user asks to check ConnectWise Automate fleet health, find stale or offline agents, report patch compliance by client, triage open alerts across clients, inventory end-of-life OSes, or see what changed overnight across an RMM fleet. Syncs your whole Automate server into a local SQLite mirror so it answers cross-client questions the per-server console can't. Trigger phrases: `connectwise automate fleet health`, `stale automate agents`, `automate patch compliance by client`, `triage automate alerts`, `use connectwise automate`, `run connectwise-automate-cli`.

Why use Connectwise Automate on TypingMind?

Because you install it once and use it with any model. Connectwise Automate 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 Connectwise Automate in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Servosity/msp-skills/tree/main/skills/connectwise-automate. 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 Connectwise Automate?

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 Connectwise Automate?

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

Is the Connectwise Automate 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 👇