What can a Cloudeval MCP-enabled agent access?

Depending on configuration and permissions, agents can query Cloudeval project, graph, report, pricing, documentation, and chat context.

Is MCP a replacement for Cloudeval reports?

No. MCP is an access layer for agents. Reports and project data remain the evidence sources the agent should use.

Should I use scoped credentials for MCP automation?

Yes. Use scoped access keys for CI or agent automation rather than broad browser-session access.

Can an MCP agent review an undeployed ARM template?

Yes, when the template is imported into a Cloudeval project. The result describes the supplied template and checks, not live runtime state.

Can Azure MCP run read-only?

Microsoft documents read-only and namespace-scoped options. Keep confirmation enabled and grant only the namespaces needed for the review.

Does Cloudeval MCP deploy resources?

No. Its documented MCP workflow is for project context, reports, diagrams and questions; it does not replace deployment approval or remediation.

Can an MCP agent review an undeployed template?

Yes, after the template is imported into a Cloudeval project. The result is limited to the supplied source and executed checks.

Does Cloudeval MCP deploy resources?

No. It provides review context, reports, diagrams and questions.

Answers

Which MCP tools help review Azure infrastructure?

Quick answer

Use Azure MCP for live Azure resources and Microsoft guidance, Bicep MCP for authoring diagnostics, and Cloudeval MCP for project diagrams, findings, reports and source-linked review questions.

Set up Cloudeval MCP Open CLI setup

Start here

Use this to

Choose a least-privilege MCP setup for inherited-environment and pre-deployment review.

Best source to use

Start with the setup guide for your exact client, then test one read-only question before giving an agent more work.

What you need

A supported MCP client such as Codex, Cursor, VS Code, or Claude Code.
Cloudeval authentication or scoped credentials.
A project, report, or docs question the agent can inspect.

What you get

Agent answers based on Cloudeval context.
Tool-backed references to docs, projects, reports, or graph data.
A safer workflow than copying private screenshots into prompts.

Get started

1
Install or configure the Cloudeval MCP client integration for the supported agent environment.
2
Authenticate with Cloudeval using normal login or scoped automation credentials where appropriate.
3
Open or create a Cloudeval project with Azure diagram, file, sync, or report context.
4
Ask the agent to inspect project, graph, report, documentation, or pricing context through Cloudeval tools.
5
Review the agent's answer and evidence before applying any recommendations.
6
Use scoped credentials and least privilege for automation.
7
Choose the server by job: Azure MCP for live Azure data, Bicep MCP for authoring diagnostics, and Cloudeval MCP for project review context.
8
Use the readonly toolset for review clients and scope project access keys to the smallest required project.
9
Ask the agent to name the project resource, report or source reference supporting each important answer.
10
Use Azure MCP read-only for live resource inventory and guidance.
11
Use Bicep MCP diagnostics while authoring a template.
12
Use Cloudeval MCP for project diagrams, reports and findings.
13
Keep client toolsets and project access keys scoped to review needs.

Helpful docs

MCP setup CLI overview support docs

When this works best

Microsoft MCP servers and Cloudeval MCP solve different jobs.

Cloudeval does not deploy or remediate, and AWS CloudFormation support is static beta.

AI Guide

Turn a diagram into a guided investigation

When a written answer is not enough, AI Guide walks through the architecture or dependency view, highlights the resources under discussion, and keeps the explanation, evidence, and next check together.

Personas adjust the emphasis for executive, architecture, security, or operations reviews. They do not change the available project evidence.

See how AI Guide works

Cloudeval Playground Architecture view with AI Guide entry point and a generated resource diagram — Real Playground capture. A guide explains available project evidence; it does not prove runtime traffic, health, or ownership.

Decision guide

Check	Cloudeval path	Note
Agent access	Configured MCP tools.	The agent only sees what credentials allow.
Best first test	Ask for docs or one report summary.	Verify setup before using project data.
Security	Scoped credentials and least privilege.	Avoid broad credentials for automation.
Decision flow	Agent prepares; user reviews.	Do not auto-apply infrastructure changes from agent text.

Choose the server by review job

Use Azure MCP read-only for live inventory, Bicep MCP while authoring, and Cloudeval MCP when the agent needs project diagrams, reports and source-linked findings.

Terminal and agent workflow

Cloudeval provides MCP setup paths for supported developer tools and agents.
The Cloudeval CLI can serve a stdio MCP workflow using this command where configured.
shell
```
cloudeval mcp serve
```
Cloudeval also exposes hosted product-docs MCP setup through the public documentation flow.

How to trust the result

Ask which resource, report, or diagram element supports the answer when it affects a decision.
Check sync time and report confidence before sharing recommendations.
Use narrow questions for specific resources, findings, or dependencies.

Frequently asked questions

What is an AI cloud architecture assistant?How do I understand an Azure environment I inherited?What can I do with the Cloudeval CLI for cloud architecture?

Start here

Use this to

Choose a least-privilege MCP setup for inherited-environment and pre-deployment review.

Best source to use

Start with the setup guide for your exact client, then test one read-only question before giving an agent more work.