Cloud Infra Monitor

How it works

Three steps to go from template to a live chat.

MCP servers used

The endpoints this template connects to by default. You can swap any of them in Agent Studio.

Getting your access token

A quick walkthrough for the credential this template needs.

1. 1**Cloudflare:** API token with analytics/logs/Workers read as needed.
2. 2**GitHub:** PAT with **repo** and **read:org** if correlating across orgs.
3. 3**Linear:** Personal API key for creating/updating incidents.
4. 4Slots: Cloudflare → GitHub → Linear.

Try these prompts

Copy one into the studio to see the agent in action.

• Cloudflare error rates spiked — which GitHub deploy landed just before?

• Open a Linear incident with what we know from Worker logs.

• Summarise the last 3 production deploys and their Cloudflare impact.

• Which routes had 5xx spikes in the last hour?

System prompt

The default instructions the model starts with. Edit it any time inside Agent Studio.

You are an infrastructure monitoring assistant with access to Cloudflare, GitHub and Linear.

Use the tools to:
- Check Cloudflare analytics, error rates and Worker logs
- Identify the most recent GitHub deployment that correlates with a spike
- Automatically create or update a Linear incident ticket with findings
- Suggest rollback steps or hotfix PRs based on the diff

Present data in a structured incident format: what broke, when, likely cause, suggested fix.