Backup Radar MCP

Backup Radar + 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 Backup Radar API. Not affiliated with, endorsed by, or sponsored by ScalePad Software Inc.

[Backup Radar demo - animated preview]

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

Also from Servosity. Backup & DR is Servosity's own field - the first-party Servosity connector brings this same fleet-wide, local-mirror approach (fleet attention, stale backups, restores, QBR reporting) to Servosity Backup and DR.

Comparing backup vendors? One of our MSP partners told us, "My guys now spend a tenth of the time on backups." Fixing is included in every Servosity co-managed backup plan, and our engineers tell you what they did. See how co-managed backup works

Every Backup Radar v3 and v2 endpoint plus a local store that finds the backups nobody is watching. 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

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

The ChatGPT desktop app runs backup-radar-mcp locally and shares MCP configuration with Codex (OpenAI). ChatGPT on the web needs a remote (HTTP) server, which msp-skills does not support yet (see mcp-install.md). 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.

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

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

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

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

macOS / Linux:

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

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

Verify:

backup-radar-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/backup-radar/install.sh)

Windows (PowerShell):

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

Inside a Hermes chat session:

/skills install servosity/msp-skills/skills/backup-radar --force

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

Install for OpenClaw

Tell your OpenClaw agent (copy this):

Install the backup-radar skill from https://github.com/servosity/msp-skills/tree/main/skills/backup-radar. The skill defines how its required CLI (backup-radar-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 (the v3 key from the ScalePad API tab, the v2 key from Backup Radar; either alone is enough for its own commands):

# macOS / LinuxBACKUP_RADAR_API_KEY=<value> BACKUP_RADAR_V2_API_KEY=<value> backup-radar-cli doctor

# Windows PowerShell$env:BACKUP_RADAR_API_KEY = "<value>"; $env:BACKUP_RADAR_V2_API_KEY = "<value>"; backup-radar-cli doctor

doctor checks config, paths and API reachability, then probes each configured key against the API (GET /clients/health for the ScalePad v3 key, GET /backups/overview for the Backup Radar v2 key) and reports valid, rejected or not verified per key (credentials, credentials_v2). The process exits 0 even when a row says ERROR; pass --fail-on error in scripts. Either key alone is enough for its own commands.

What this skill does

Every analysis command reads the local mirror that backup-radar-cli sync fills from whichever keys you set, and each one says which collections it skipped because they were never synced. The mirror is scoped to the credentials that filled it (the v3 key, and the v2 key when one was set), so run the analysis commands with the same BACKUP_RADAR_API_KEY (environment or auth set-token) and the same BACKUP_RADAR_V2_API_KEY setting that sync used.

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 Backup Radar 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 our 400 backups has been silent for a week with no ticket, and which client's compliance rate fell last quarter".

This skill syncs Backup Radar 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 check, unwatched and scorecard join across the ScalePad v3 client-health and device history and the Backup Radar v2 backup status, inactive list, policy flags and ticket counts - work a stateless API wrapper can't do, because the two API generations never answer in one call.

The pain this closes

A backup that never reports sends no failure email. ScalePad's Gflex partner story describes backups that went unnoticed for weeks or months until no-result monitoring caught them, and a technician who spent about four hours a day sorting backup mail; MicroAge Swift Current put its manual review at two hours a day. Backup Radar closes the collection gap, but the morning review is still a person in a portal: which failures are new, which have run for a week, which already have a ticket, which backups were never activated, and which decommissioned devices are still generating no-result noise. River Run only acts on failures that persist past a day because a single failed run usually self-corrects, which is exactly the new-versus-ongoing judgment the portal leaves to the technician.

What this skill does about it:

• backup-radar-cli check --include-at-risk --agent - today's failing, silent and at-risk backups ranked, each marked new or ongoing with days in status and open ticket count (without --include-at-risk, only failing and no-result backups).
• backup-radar-cli unwatched --agent - every backup nobody acts on, with a reason code: inactive, unmapped, ticketless, no-psa, masked.
• backup-radar-cli stale --days 45 --agent - silent backups grouped by client, each with a dry_run: true retire body (pinned by ScalePad device id for mapped devices, by exact company, device and job name for unmapped ones; v2-only rows get a retire_note instead), ready to preview with backups retire --stdin.
• backup-radar-cli scorecard --days 90 --agent - every client ranked by in-compliance rate, or one client's weekly trend and worst devices for the QBR.
• backup-radar-cli coverage diff --devices vendor-devices.json --agent - the devices your backup vendor protects that Backup Radar never sees, and the reverse.

See pain-point.md for the longer narrative.

Frequently asked questions

Does this work with ChatGPT?

Yes, in the ChatGPT desktop app. It runs MCP servers locally (STDIO), the way backup-radar-mcp runs, and shares MCP configuration with Codex (OpenAI): add backup-radar-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 (HTTP) server, which msp-skills does not support yet (see mcp-install.md). If your team works there, a hosted gateway is the better pick; check that your AI app is on the gateway's setup list.

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 Backup Radar credentials once.

Is my Backup Radar 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.

Do I need both a ScalePad API key and a Backup Radar API v2 key?

No. The ScalePad API key (BACKUP_RADAR_API_KEY, v3) powers health, devices, backups ingest, backups retire and push. The Backup Radar API v2 key (BACKUP_RADAR_V2_API_KEY) powers backups list, get, results, filters, inactive, retired and overview. Either key alone runs its own commands; check, unwatched, stale and timeline use whichever data you synced and list what they skipped.

Will this hit my Backup Radar or ScalePad API rate limits?

The analysis commands read the local mirror, so the daily API cost is one sync: v3 client health with a year of history, v3 devices with 90 days, and the v2 backups lists with 31 days. The client sends at most 2 requests per second by default (--rate-limit).

Can an AI agent retire backups by mistake?

backups retire is the only command that removes backups from monitoring, and it is a v3 write that supports the API's own preview, --server-dry-run (the request is sent and nothing is retired; the global --dry-run sends nothing). stale prepares retire bodies with dry_run: true, pinned by ScalePad device id for mapped devices and by exact company, device and job name for unmapped ones; a backup it cannot pin gets a retire_note instead of a body. Over MCP, BACKUP_RADAR_MCP_READ_ONLY=1 removes the backups_retire and backups_ingest tools entirely, and backups_retire is annotated destructive so hosts ask first.

Does it work for EU ScalePad tenants?

Yes. Set BACKUP_RADAR_BASE_URL to https://eu.api.scalepad.com/backup-radar/v3 (the default is the US host). The Backup Radar API v2 has a single host, https://api.backupradar.com.

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

Over MCP, BACKUP_RADAR_MCP_READ_ONLY=1 removes backups_ingest, backups_retire, sync, export, workflow_archive and the learning-store write tools (teach, teach_pattern, teach_lookup, teach_playbook, playbook_amend, learnings_confirm, learnings_forget, learnings_reject); the push and import commands are never exposed over MCP, and flags that read or write local files (--devices, --playbook-file, --notes-file, --output, --db) are refused from MCP callers.

The strongest control is the scope you grant the Backup Radar 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

Beta. Validated against the Backup Radar 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: 2026-10-19.