SuperOps MCP

SuperOps + 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 SuperOps API. Not affiliated with, endorsed by, or sponsored by SuperOps Inc.

[SuperOps demo - animated preview]

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

Every SuperOps PSA+RMM entity in your terminal, plus a local SQLite mirror that answers cross-entity questions the web UI can't. 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. Local agents use the default stdio transport and need no network listener. HTTP mode (--transport http, for remote agents) refuses to start until SUPEROPS_MCP_HTTP_TOKEN is set to a random token of at least 32 characters, rejects any request without that bearer token, serves http://127.0.0.1:7777/mcp by default, and needs --tls-cert and --tls-key for any other address. It refuses a request body over 4 MiB or one that takes longer than 30 seconds to arrive. Whoever holds the token can call every tool with your SuperOps credentials, including tools that change your tenant, so treat it like a password, and set SUPEROPS_MCP_READ_ONLY=1 on a remote host that only needs to read. See mcp-install.md.

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

The ChatGPT desktop app runs superops-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 superops-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 SUPEROPS_CLI_PATH to an existing binary). Details: #331.

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

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

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

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

macOS / Linux:

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

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

Verify:

superops-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/superops/install.sh)

Windows (PowerShell):

iwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/superops/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 superops@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/superops --force

Inside a Hermes chat session:

/skills install servosity/msp-skills/skills/superops --force

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

Install for OpenClaw

Tell your OpenClaw agent (copy this):

Install the superops skill from https://github.com/servosity/msp-skills/tree/main/skills/superops. The skill defines how its required CLI (superops-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 - a SuperOps API token (Settings > My Profile > API token) and your tenant subdomain (Settings > MSP Information):

export SUPEROPS_API_TOKEN=<your api token>export SUPEROPS_SUBDOMAIN=<your tenant subdomain>   # sent as the CustomerSubDomain headerexport SUPEROPS_REGION=us                            # or eu for euapi.superops.ai (us is the default)superops-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. The scope of the token you mint is the permission boundary - the CLI can only do what that token is allowed to do.

What this skill does

Beyond the views: every SuperOps PSA+RMM entity - tickets, assets, alerts, clients, sites, users, contracts, invoices, worklogs, technicians, service items, IT docs, KB - is a typed list/get subcommand, and raw query runs any GraphQL read the typed commands don't wrap. The commands are also available as MCP tools.

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 SuperOps integrations and MCP servers proxy each question into a live GraphQL call. That's fine for one record. It dies at scale, when you're asking "which open tickets across every client are about to breach SLA, and on whose queue" - the API rate-limits reads, and its list payloads don't even carry some of the cross-entity links that question needs.

This skill syncs SuperOps 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 sla-watch, client-360, and at-risk-assets join across tickets, SLAs, technicians, clients, contracts, assets, alerts, and invoices - work a stateless API wrapper can't do.

The pain this closes

SuperOps' pitch is one database for PSA and RMM - and that part is real. But the console still answers one entity at a time, and the platform's own AI is, as third-party reviewers put it, "more roadmap than reality" (Flamingo, "SuperOps Review for MSPs," 2026). So the questions you actually ask at month-end or before a QBR are still cross-entity questions no single console screen composes: who's about to miss SLA and on whose queue, how much billable time is sitting unreconciled for a client, which endpoints are both unpatched and actively alerting. And the GraphQL API makes the do-it-yourself version painful - it rate-limits reads and omits some of the very links those questions need (asset-to-ticket, aggregated child-activity timestamps), so any script has to fetch, cache, and join locally.

What this skill does about it:

• superops-cli sla-watch --by tech --window 4h - every open ticket breaching or about to breach its resolution SLA, grouped by technician. The dispatcher's morning triage.
• superops-cli client-360 "Acme Corp" - the client plus its sites, users, contracts, open tickets, assets, and open invoices in one bundle. Six console tabs in one command.
• superops-cli at-risk-assets --client Acme - endpoints whose patch status signals a missing/critical patch that also carry an unresolved alert. Remediation, prioritized.
• superops-cli unbilled --since 2026-05-01 - billable logged worklog totaled per client (the reconciliation target), so you see where billable time is concentrated before the invoice run.

The first run, a sync pulls your tenant into local SQLite; after that these views run offline, instant, and free of rate limits.

See pain-point.md for the longer narrative.

Known gaps (honest limits)

These views are computed from what the SuperOps list API actually exposes, and the CLI is candid about its proxies:

• unbilled surfaces billable logged time per client, not a strict worklog-minus-invoice diff - the API carries no per-entry "already billed" flag.
• at-risk-assets and alert-coverage use an unresolved alert as the proxy for "currently causing pain," because the asset-to-ticket link is absent from the list payloads.
• context-ticket bundles the synced ticket, its worklogs, client, and SLA; conversation and note threads are not included; read them in the SuperOps console or with superops-cli raw query.

Frequently asked questions

Does this work with ChatGPT?

Yes, in the ChatGPT desktop app. It runs MCP servers locally (STDIO), the way superops-mcp runs, and shares MCP configuration with Codex (OpenAI): add superops-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 SuperOps credentials once.

Is my SuperOps 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.

Will this hit my SuperOps API rate limits?

The local mirror exists so reads stop hitting the API. After the first sync, the cross-entity views (sla-watch, client-360, at-risk-assets, alert-coverage, unbilled, stale-tickets) 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 it treats resources your token can't reach as warnings, not failures.

Does it work with the US and EU SuperOps regions?

Yes. The US host is the default; set SUPEROPS_REGION=eu to target the EU host (euapi.superops.ai). Your tenant subdomain goes in SUPEROPS_SUBDOMAIN, which the CLI sends as the CustomerSubDomain header on every request.

Can it create or update tickets?

The typed commands are read-only by design - inspection, export, sync, and analysis. The one write path is raw mutation, the supported escape hatch for operations the typed commands don't wrap (for example createTicket, updateTicket, resolveAlerts). Without --yes it prints the exact GraphQL request and sends nothing; add --yes to send. Over MCP, raw_mutation can only preview (the MCP server never passes --yes), and GraphQL variables go inline in the document because the separate vars field is not offered there. raw query is the read-only counterpart and refuses any document that is not a query. Keep a human in the loop for every send.

Will this replace my SuperOps console?

No - and it isn't trying to. The console stays best for in-app workflows like dispatch, time entry, and invoicing. This skill brings your tenant's data to whichever AI agent you already use, and answers the cross-entity questions - joined across PSA and RMM - that no single console screen composes today.

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

Every typed command is read-only; the binary's one path to remote change is raw mutation, which prints the exact GraphQL request and sends nothing unless you add --yes. Over MCP it can only preview, so an agent connected over MCP cannot send a mutation. Put the remaining gate in your policy: preview, show the request, get approval, then run with --yes.

The strongest control is the scope you grant the SuperOps 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 @AvlCompCo (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.