SaaS Alerts MCP

SaaS Alerts + 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 SaaS Alerts

API. Not affiliated with, endorsed by, or sponsored by Kaseya US LLC.

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

All four SaaS Alerts APIs (Reports, Manage, Respond and Webhooks) in one CLI and MCP server, plus cross-customer alert triage, the Respond approval queue sorted by deadline, and preview-first account containment. 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 saas-alerts-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 SaaS Alerts MCP (.mcpb) - then open Claude Desktop > Settings > Extensions and select the file. One click, no JSON, no shell. (Browse every SaaS Alerts 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 saas-alerts@msp-skills

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

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

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

macOS / Linux:

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

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

Verify:

saas-alerts-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/saas-alerts/install.sh)

Windows (PowerShell):

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

Inside a Hermes chat session:

/skills install servosity/msp-skills/skills/saas-alerts --force

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

Install for OpenClaw

Tell your OpenClaw agent (copy this):

Install the saas-alerts skill from https://github.com/servosity/msp-skills/tree/main/skills/saas-alerts. The skill defines how its required CLI (saas-alerts-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 partner API key from the SaaS Alerts dashboard (Settings > API, GET APIKEY; SaaS Alerts shows the key only until you leave the page, so copy it then):

SAAS_ALERTS_API_KEY=<value> saas-alerts-cli doctor

On Windows (PowerShell):

$env:SAAS_ALERTS_API_KEY = "<value>"

saas-alerts-cli doctor

doctor checks config, paths and API reachability, and sends the key to the Reports API's partner profile endpoint, so a rejected key shows up as a Credentials: invalid row. It exits 0 even then, so scripts should add --fail-on error. The Respond access token is minted on the first Respond call, not by doctor; saas-alerts-cli respond status confirms Respond works end to end.

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 SaaS Alerts integrations and MCP servers proxy each question into a live API call. That's fine for one record. It dies at scale, when you're asking "which of my 80 customers had a critical alert overnight, and is the same IP behind more than one of them".

This skill syncs customers, events, users and Respond triggers into a local SQLite store, so triage, cross-tenant, investigate and coverage answer across every customer in one local query, and say synced: false instead of an empty all-clear when the data was never synced. It covers all four SaaS Alerts APIs with one partner key: it mints the Respond access token itself (Respond answers "Only secure origins are allowed" to a call that carries only the API key), works the Respond queue by deadline with rule-triggers queue, and previews every change rule-triggers decide and contain would make until you add --confirm.

WYRE-AI's saas-alerts-mcp, which also backs the SaaS Alerts plugin in their msp-claude-plugins marketplace, exposes the SaaS Alerts External Partner API as 30 tools across customers, events, users, devices, billing, scheduled reports and partner settings, with no Respond, suppression or webhook tools; it runs locally with your own key, or through WYRE's hosted Conduit gateway when used from their plugin. This one adds Respond, suppressions and webhooks. It complements the SaaS Alerts dashboard rather than replacing it: the dashboard stays the place to configure monitoring, review alerts and set up R