Cloudback MCP Backup Coverage Review
Review Cloudback backup coverage with a Docker-based MCP server, gate configuration changes with HITL, and notify ops in Slack.
The full canvas, before you import it
Click any node to see its config.
Click a node to select it — same as the Heym editor; the panel shows its settings.
5 nodes · Free & source-available
Cloudback MCP Backup Coverage Review
Review Cloudback backup coverage through the Cloudback MCP Docker server, identify backup definitions with disabled or failed backups, ask for human approval before configuration changes, and notify the engineering team through Slack.
What this workflow does
- cloudbackConfig collects the full
Platform::Account::ApiKeyaccount entry and the review scope - cloudbackOpsAgent starts
myrtlelabs/cloudback-mcpover stdio and uses Cloudback MCP tools for backup, storage, schedule, and account review - The Agent treats read/list/view actions as safe, but asks for human approval before update, create, delete, storage, schedule, account-setting, or bulk-change MCP calls
- notifyCloudbackReview posts the review URL and proposed action to Slack when HITL approval is needed
- cloudbackAuditReport returns the final reviewed backup report and decision metadata for traceability
Use cases
- Backup coverage reviews for GitHub, Linear, GitLab, or Azure DevOps accounts
- Detecting backup definitions with disabled or failed backups across supported platforms
- Safe ops automation where an agent can recommend changes but humans approve writes
- Demoing Docker-based stdio MCP servers inside Heym
MCP setup
Cloudback expects OpsApi__BaseUrl and one or more OpsApi__Account__N values. It does not read CLOUDBACK_API_KEY. Each connected account needs its own Operations API key generated from the Cloudback dashboard at app.cloudback.it/apikeys. There is no single global key across every organization, group, or workspace.
Because this template launches the MCP server through Docker, the values must be forwarded into the container with docker run -e flags:
{
"args": [
"run",
"--platform",
"linux/amd64",
"-i",
"--rm",
"--pull=always",
"-e",
"OpsApi__BaseUrl=https://app.cloudback.it/",
"-e",
"OpsApi__Account__1",
"myrtlelabs/cloudback-mcp"
],
"env": {
"OpsApi__Account__1": "$cloudbackConfig.body.accountEntry"
}
}Enter the account entry as the full Platform::Account::ApiKey string, for example GitHub::your-org::your-cloudback-api-key. Supported platforms include GitHub, AzureDevOps, GitLab, and Linear.
For multiple accounts, add separate entries such as OpsApi__Account__1=GitHub::org-a::key-for-org-a and OpsApi__Account__2=GitLab::group-b::key-for-group-b. Each key should be generated for that specific account in Cloudback.
Setup
Connect an LLM credential in cloudbackOpsAgent, add a Slack credential in notifyCloudbackReview, and replace the placeholder accountEntry value with a key from app.cloudback.it/apikeys before running. The Cloudback MCP server is pulled with Docker, so the Heym runtime needs Docker access.
How to import this template
- 1Click Import → Copy JSON on this page.
- 2Open your Heym and navigate to a workflow canvas.
- 3PressCmd+V/Ctrl+V— nodes appear instantly.
- 4Add your API keys in the node config panels and click Run.
Discover more automations
- Dev & IT OpsCursor Post NotifierMonitor the Cursor blog on a schedule and Slack-notify your team when a new post goes live.
- Dev & IT OpsClaude Blog MonitorMonitor the Anthropic blog on a schedule and Slack-notify your team on new Claude posts.
- Dev & IT OpsGitHub Release RadarCompare the latest GitHub release tag against Redis and notify Slack when a project ships a new version.
- Dev & IT Opsweb.dev Article MonitorCron + crawler + Redis dedupe + Slack: get notified when Google's web.dev blog publishes a new article.
- Dev & IT OpsResilient HTTP + Error HandlerAttach an Error Handler node to an HTTP call and Slack-notify your team the moment a request fails.
- Dev & IT OpsPlaywright Visual AI MonitorTake a full-page screenshot on a schedule, analyse it with an LLM for anomalies, and Slack-alert when something looks off.
- Dev & IT OpsRealtime WebSocket Alert RelayListen to an external WebSocket feed, audit critical events, and forward them to another realtime channel.
- Dev & IT OpsAsync Sub-workflow DispatcherValidate an incoming brief and dispatch a reusable sub-workflow in the background without a response node.
- Dev & IT OpsRabbitMQ Delayed PublisherPublish a release message to RabbitMQ with an optional delivery delay for downstream consumers.
- Dev & IT OpsSelf-stopping Status MonitorPoll an incident endpoint until it resolves, then automatically disable the polling trigger for future runs.
- Dev & IT OpsEjentum Code ReviewerA 4-agent MAS that refuses to rubber-stamp PRs: architect orchestrates three cross-lab specialists (reasoning, code, anti-deception), each backed by the Ejentum Logic API.
- Dev & IT OpsCoding Agent with GitHub IntegrationReceive a plain-English coding task, plan with Sequential Thinking, write and commit code via GitHub MCP, then post a Slack summary.