Updated May 12, 2026
What can I do with the Cloudeval CLI for cloud architecture?
Quick answer
Use the Cloudeval CLI to create projects, run diagnostics, open diagrams, run reports, ask project questions, and export diagrams from the terminal.
It can also serve MCP workflows for compatible agent tools.

What you can expect
A practical path from source input to diagram, report context, docs, exports, and the first AI question to ask.
Start here
Use this to
Run Cloudeval architecture workflows without relying only on the browser UI.
Best source to use
Check the CLI overview and command reference before scripting automation, then run one project command by hand.
What you need
- Cloudeval CLI installed.
- Cloudeval login or scoped access key.
- A project source or project ID.
What you get
- Project creation or inspection from the terminal.
- Reports, questions, sessions, or exports from CLI commands.
- MCP serving when agents need tool access.
Fastest path to a useful result
- 1Install the CLI.
- 2Run login and doctor/status checks.
- 3Create or open one project.
- 4Run one report or export one diagram.
When this works best
Use this when you want terminal automation for projects, reports, questions, exports, and MCP.
Provider import behavior still depends on current Cloudeval support.
Decision guide
| Check | Cloudeval path | Note |
|---|---|---|
| Setup | Install, login, run doctor/status. | Do this before automation. |
| Project work | Create, open, inspect, or link a project. | Use project IDs for repeatable workflows. |
| Reports and AI | Run reports and ask project questions. | Prefer specific prompts. |
| Exports and agents | Export diagrams or serve MCP. | Use scoped credentials in CI. |
Who this is for
- CLI-first developers
- Platform engineers
- Automation authors
- AI agent operators
How it works
- 1Install the Cloudeval CLI from the public install flow.
- 2Run setup, login, status, and doctor commands before relying on automation.
- 3Create or inspect Cloudeval Azure projects from the terminal.
- 4Run reports or ask project questions with project IDs.
- 5Export architecture or dependency diagrams when a headless workflow needs image files.
- 6Configure MCP serving when an agent needs tool access through the CLI.
Terminal-first architecture review
A developer can create a Cloudeval project from ARM JSON, run reports, open the project diagram, export an architecture image, and ask a project question from the terminal.
This avoids clicking through every app surface for repeated work.
Terminal and agent workflow
This command creates Cloudeval projects from supported sources.
shellcloudeval projects createThis command runs report workflows for a project.
shellcloudeval reports runThis command sends one-shot project questions.
shellcloudeval askThis command exports architecture or dependency diagram images.
shellcloudeval projects export-diagramThis command supports stdio MCP workflows where configured.
shellcloudeval mcp serve
How to trust the result
- Run one command manually before putting it into CI or an agent workflow.
- Keep project IDs, account details, IPs, and resource names out of public exports unless they are sanitized.
- Link exported diagrams back to the Cloudeval project or report when reviewers need details.
FAQ
Can the CLI export diagrams?
Yes.
The Cloudeval CLI includes project diagram export workflows for architecture and dependency layouts.
Can the CLI ask architecture questions?
Yes.
This command supports project questions against available Cloudeval project context.
cloudeval askCan I use the CLI in automation?
Yes.
Use non-interactive flags, doctor checks, and scoped access keys for automation-friendly workflows.
Related pages
Build this workflow in Cloudeval
Start with a Cloudeval Azure project, then connect diagrams, reports, source links, CLI automation, and MCP-compatible agent workflows around the same source of truth.
