ConnectWise RMM MCP

ConnectWise RMM + 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 ConnectWise RMM

(Asio) partner API. Not affiliated with, endorsed by, or sponsored by ConnectWise, LLC.

Full skill page - install, outcomes, safety model.

66 ConnectWise RMM (Asio) partner API operations, plus a local fleet database, patch-compliance rollups, and script runs you can preview, schedule and watch in one command. 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

Security note (until this connector is reprinted). Do not run HTTP mode

(--transport http), not even on localhost. This build checks a token, but it

predates the fix release's request size and time limits. The MCP tools can

also make changes with your credentials. Use the default stdio transport. If

you set up a tunnel for a remote agent, shut it down. A fix is on the way.

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

The ChatGPT desktop app runs connectwise-rmm-mcp locally and shares MCP configuration with Codex (OpenAI). ChatGPT on the web needs a remote (HTTP) server, and this connector's HTTP mode is paused until it is reprinted (see the security note in mcp-install.md), so msp-skills does not support it 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.

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](../../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

Download ConnectWise RMM MCP (.mcpb) - then open Claude Desktop > Settings > Extensions and select the file. One click, no JSON, no shell. (Browse every ConnectWise RMM 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 connectwise-rmm@msp-skills

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

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

Install the ConnectWise RMM 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-rmm/install.sh). If it uses Windows PowerShell, run iwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/connectwise-rmm/install.ps1 | iex. Then authenticate per the README and run connectwise-rmm-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/connectwise-rmm/install.ps1 | iex

macOS / Linux:

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

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

Verify:

connectwise-rmm-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/connectwise-rmm/install.sh)

Windows (PowerShell):

iwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/connectwise-rmm/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 connectwise-rmm@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](./mcp-install.md) and [docs/which-agent.md](../../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/connectwise-rmm --force

Inside a Hermes chat session:

/skills install servosity/msp-skills/skills/connectwise-rmm --force

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

Install for OpenClaw

Tell your OpenClaw agent (copy this):

Install the connectwise-rmm skill from https://github.com/servosity/msp-skills/tree/main/skills/connectwise-rmm. The skill defines how its required CLI (connectwise-rmm-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

Create an API client under Integrations > API Access in the ConnectWise portal, then set its ID and secret:

CONNECTWISE_RMM_CLIENT_ID=<value> CONNECTWISE_RMM_CLIENT_SECRET=<value> connectwise-rmm-cli doctor

A client ID starting 0e30, 0e31 or 0e32 picks North America, Europe or Australia for you; if yours starts differently, set CONNECTWISE_RMM_BASE_URL to your region's API host. If your key was not granted every scope this connector uses, run connectwise-rmm-cli scopes --agent and set the CONNECTWISE_RMM_OAUTH_SCOPE line it prints - ConnectWise rejects a whole token request that asks for one scope the key lacks. Then pull the fleet into the local mirror:

connectwise-rmm-cli sync --resources companies,sites,endpoints,tickets

doctor mints a token from your client ID and secret and verifies it against the API, so a wrong secret, a missing scope or a wrong host shows up as a failed Credentials line. It exits 0 even when a check fails, 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 ConnectWise RMM integrations and MCP servers - the open-source connectwise-asio-mcp and asio-cli among them - work against the live API with no persistent local copy. That's fine for one device. It dies at scale, when you're asking "which agents are offline across all 40 clients" or "who's behind on patches before this morning's client review", because Asio returns per-endpoint rows keyed by IDs, never a per-client roll-up, and caps availability checks at 400 endpoints per call.

This skill syncs ConnectWise RMM into a local SQLite mirror with full-text search, batches the live availability checks, and caches patch summaries. Aggregate questions become one local join, and the AI sees the answer, not the raw data. Compound commands like fleet patch-posture, fleet scorecard, and fleet task-failures join companies, sites, endpoints, patch summaries, tickets and task results - work a stateless API wrapper can't do.

The pain this closes

ConnectWise RMM (the cloud RMM on the ConnectWise Asio platform, formerly Command and Continuum) is built around a per-client, per-device view, and its partner API is the same shape: ConnectWise's own docume