Why this matters
Insights are how your team tracks interesting observations, analysis and optimization work in CloudZero. Each one records the opportunity and its status, so the work gets sized, assigned, and closed out.
Teams now do a lot of this work in an AI assistant. For example, you can ask Claude which instances sat idle last month, and it will tell you. But if you have to switch to CloudZero and fill out a form to log that finding, some findings won’t get logged. Your team can’t track insights it never logged.
What we built
The CloudZero MCP server can now create, update, and delete Insights. Ask your assistant to log a finding as an Insight, and it fills in the description, status, and effort for you. Later, ask it to move an Insight to a new status, change the effort, or rewrite the description as the work changes.
Say your assistant finds a trend of growing spend for a given account attributed to some deprecated idle databases. You can ask it to log an Insight. Then, at your weekly cost review, you can ask your team what progress has been made and have the assistant mark it resolved. Your Insights list in CloudZero stays up to date.
How it works
Connect your AI tool to the CloudZero MCP server, then ask it to create, update, or delete an Insight. Your account needs full data access to make changes.
See it in the docs → https://docs.cloudzero.com/docs/ai-mcp-server
