dbx
Query databases from AI agents using connections configured in DBX.
T8t8y2/dbx26k1,070 new stars in the last 7 days
Every Atera RMM + PSA endpoint, plus a local SQLite mirror that answers fleet-health, SLA, and
Unofficial. Community-built Claude Code Skill and MCP server for the Atera API. Not affiliated with, endorsed by, or sponsored by Atera Networks Ltd.
▶ Watch the 30-second demo - demo data is simulated; every command shown exists in the real CLI.
Every Atera RMM + PSA endpoint, plus a local SQLite mirror that answers fleet-health, SLA, and book-of-business questions no single API call can. Works with the AI you already use - ChatGPT (Plus/Pro+), Claude Desktop, Codex, Claude Code, Claude Cowork, and GitHub Copilot - plus Microsoft 365 Copilot / Copilot Studio and Google Gemini via the remote path. Free, open source, runs on your laptop. Built for MSP owners. No code required.
The six agents MSP owners actually use (self-serve, works today):
| Your AI agent | How to install the Atera skill |
|---|---|
| Claude Desktop | Run installer, then Settings > Extensions to register atera-mcp (no JSON editing). |
| ChatGPT (paid plans) | Run installer, expose atera-mcp over HTTPS, register as a Developer Mode connector. |
| Codex CLI | Paste the install prompt below. |
| Claude Code | Paste the install prompt below. |
| Claude Cowork | Paste the install prompt below. |
| GitHub Copilot (VS Code) | Run installer, add atera-mcp to mcp.json under the servers key, then pick Agent mode. |
For ChatGPT, run atera-mcp --transport http and expose that behind HTTPS - no bridge package is needed. See mcp-install.md.
Big install base, but an honest heads-up: these are the remote / enterprise path, not the local binary you just installed.
| Agent | What it takes |
|---|---|
| Microsoft 365 Copilot / Copilot Studio | Not self-serve. Host atera-mcp over HTTPS, then wire it into Copilot Studio (Tools > Add a tool > Model Context Protocol > Server URL) or a declarative agent. Needs a Copilot Studio license + tenant admin. See mcp-install.md. |
| Google Gemini | Gemini CLI is local - same as Claude Code. The Gemini app is remote - same HTTPS path as ChatGPT. See mcp-install.md. |
Skill-native agents (also covered): Hermes and OpenClaw read this skill's
SKILL.mddirectly 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.
.mcpbClaude Desktop bundle: the
.mcpblaunches on macOS (Intel and Apple Silicon), Windows x64 and Linux x64. Every tool shells out to the companionatera-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 setATERA_CLI_PATHto an existing binary). Details: #331.
Download Atera MCP (.mcpb) - then open Claude Desktop > Settings > Extensions and select the file. One click, no JSON, no shell. (Browse every Atera 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 atera@msp-skills
Copy this into Claude Code, Codex CLI, or Claude Cowork:
Install the Atera 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/atera/install.sh). If it uses Windows PowerShell, runiwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/atera/install.ps1 | iex. Then authenticate per the README and runatera-cli --helpto explore.
The same prompt works in any agent that can run shell.
Windows (PowerShell):
iwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/atera/install.ps1 | iex
macOS / Linux:
bash <(curl -fsSL https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/atera/install.sh)
The installer drops both atera-cli (the CLI) and atera-mcp (the MCP server) into your user bin path. Claude Code, Codex, and Cowork discover the Skill via SKILL.md in this directory.
Verify:
atera-cli --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/atera/install.sh)
Windows (PowerShell):
iwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/atera/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 atera@msp-skills.
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 remote Microsoft 365 Copilot / Copilot Studio path. 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.
From the Hermes CLI:
hermes skills install servosity/msp-skills/skills/atera --force
Inside a Hermes chat session:
/skills install servosity/msp-skills/skills/atera --force
Hermes speaks MCP natively, so it can also use the atera-mcp server directly - same install path, same env vars.
Tell your OpenClaw agent (copy this):
Install the atera skill from https://github.com/servosity/msp-skills/tree/main/skills/atera. The skill defines how its required CLI (
atera-cli) can be installed via theopenclaw:frontmatter block.
OpenClaw isn't generally available yet; the frontmatter wiring is pre-shipped and will activate the moment OpenClaw launches.
Create an API key in your Atera portal under Admin → API, then set it and confirm it works:
ATERA_API_KEY=<your-key> atera-cli doctor
doctor confirms the credential works and the API is reachable before you run anything that touches data. It exits 0 even when the credential is rejected, so scripts should add --fail-on error. You can also persist it with atera-cli auth set-token.
| Question your MSP keeps asking | Command |
|---|---|
| Which agents have gone offline or stopped checking in? | atera-cli agents stale --days 30 |
| Which open tickets are closest to breaching SLA? | atera-cli tickets sla |
| Who is overloaded on the service desk right now? | atera-cli tickets workload |
| Which customers have managed agents but no active contract? | atera-cli customers coverage |
| What contracts expire in the next 60 days? | atera-cli contracts expiring --days 60 |
| What's my full book of business by customer and contract mix? | atera-cli customers book |
| Where are the chronic machines generating the most alerts? | atera-cli agents noisy --days 7 |
| What's the patch-compliance picture across the fleet? | atera-cli agents patch-status |
| Which machines are running an end-of-life OS? | atera-cli agents inventory --eol |
| What changed across agents, tickets, and alerts since yesterday? | atera-cli since 24h |
Full command reference: guide.md. For the AI-agent operating contract (--agent, --dry-run, when to confirm before mutating), see AGENTS.md.
Most Atera 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 customers across all 40 clients have managed agents but no active contract" or "what's about to breach SLA right now."
This skill syncs Atera 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 customers coverage, customers book, and agents noisy join across customers, contracts, agents, and alerts - work a stateless API wrapper can't do.
Atera's reporting is the consistent gripe in G2 and Capterra reviews: custom reports need workarounds, filtering is rigid, exports are clunky, and the deeper cross-client analytics sit behind higher-tier plans. There's no single screen that answers "which machines went dark," "which tickets breach SLA next," or "which customers are under-contracted" across every client at once - you assemble it by hand, portal tab by portal tab.
This skill closes that gap with cross-client rollups that run offline against the local mirror:
atera-cli agents stale --days 30 - the machines that quietly stopped reporting, before the client calls.atera-cli tickets sla - open tickets ranked by minutes-to-breach, soonest first.atera-cli customers coverage - accounts you manage but don't bill: managed agents, no active contract.atera-cli contracts expiring --days 60 - the renewal calendar Atera never shows as one view.atera-cli agents patch-status - fleet-wide missing-patch rollup the API has no single endpoint for.See pain-point.md for the longer narrative.
Yes, on Plus, Pro, Team, Business, Enterprise, and Education plans (Free tier does not yet expose Developer Mode). ChatGPT connects to remote MCP servers over HTTPS, not local stdio binaries. The Atera MCP server runs locally, but it speaks HTTP natively: start it with atera-mcp --transport http --addr :7777 and put it behind an HTTPS tunnel or your own reverse proxy. No bridge package is involved. Step-by-step in mcp-install.md.
Yes - all of them speak MCP. Cross-tool install commands are in the matrix above and the deep-dive in docs/which-agent.md.
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 Atera credentials once.
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.
Rarely. Most questions run against the local SQLite mirror after a one-time sync, so they make zero API calls. The few commands that fetch live (like agents patch-status) are paced under Atera's 700-requests-per-minute limit.
No. You need an Atera account and an API key created under Admin → API. Any plan that exposes the API works; nothing here requires a special partner tier.
No - it complements it. The portal stays your system of record and remote-access console; this skill adds the cross-client, terminal-and-AI query layer the portal doesn't offer.
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.
| Tier | Examples | Recommended agent policy |
|---|---|---|
| Read | agents stale, tickets sla, customers coverage, contracts expiring, since, search, sync, every get-/rollup command | Allow |
| Write (routine) | tickets post/put, contacts post/put, customers post/put, contracts post/update, alerts post/resolve, devices create-*, customvalues set-*, import | Preview with --dry-run, then a reviewed write |
| Destructive / config | agents delete, tickets delete, customers delete, devices delete-*, and credential changes (auth set-token, auth setup, auth logout) | Human-in-the-loop only |
The strongest control is the scope you grant the Atera 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.
Beta. Validated against the Atera API surface and being validated with MSPs running it live against their own production tenant 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: 2026-06-06.
Query databases from AI agents using connections configured in DBX.
T8t8y2/dbx26k1,070 new stars in the last 7 days
MCP Toolbox for Databases enables your agent to connect to your database.
GOgoogleapis/mcp-toolbox17k56 new stars in the last 7 days
Real-time Kubernetes network traffic visibility and API analysis for HTTP, gRPC, Redis, Kafka, DNS.
KUkubeshark/kubeshark12k7 new stars in the last 7 days
Let your users work with their own data through an AI assistant, limited to what they can see.
NHnhost/nhost9.4k10 new stars in the last 7 days
Open-source desktop SQL workspace with 3 built-in database drivers and 16 shipped plugins, including SQL Server, DuckDB, ClickHouse and Redis. Built-in MCP server for Claude, Cursor and Devin, SQL notebooks and visual EXPLAIN.
TATabularisDB/tabularis5.2k81 new stars in the last 7 days
Manage Jitsu data pipelines: destinations, streams, connections, functions, live events.
JIjitsucom/jitsu5.1k8 new stars in the last 7 days