MCP server · Security · official

Shieldly MCP server

Lets your AI check AWS IAM policies and CloudFormation templates for risky permissions.

Security Developer tools For it and development Security

Shieldly is an official helper that lets your AI assistant look over your AWS permissions and tell you what looks risky. It checks IAM policies and CloudFormation templates for things like wildcards and paths that could let someone give themselves more access. It is handy if you work with AWS and want a second pair of eyes without learning a security tool.

What is an MCP server? The 30-second version

On its own, your AI can only chat. An MCP server is a small helper program that gives your AI a new skill or a connection to a service. This one connects your AI to Shieldly, a security analysis service for AWS. Once it is set up, you can paste in a policy or template and ask your AI to check it, and the AI passes it to Shieldly and brings the answer back to you.

What this MCP server does

You paste an AWS IAM policy or a CloudFormation template into your chat and ask your AI to review it. Your AI sends the text to this helper, which forwards it to Shieldly for analysis. Shieldly looks for privilege escalation paths, wildcards, and other signs of over-permissive access. The result comes back into your chat as a written summary of the findings. You can then ask follow-up questions or fix the policy and check it again.

Flow diagram: you ask your AI “Check my IAM policy for security problems”, the Shieldly MCP server connects it to Shieldly, and you get back A written summary of issues.

Click to zoom

What you can do with it

Check an IAM policy for wildcards and over-permissive access
Spot privilege escalation paths in a policy
Review a cross-account trust and identity policy pair
Scan a CloudFormation template for risky IAM roles and policies
Get a plain-language summary of what looks wrong
Re-check a policy after you edit it

Try asking your AI

“Here is my IAM policy, can you check it for security problems?”
“Does this policy allow anyone to escalate their privileges?”
“Review this CloudFormation template and flag any over-permissive IAM roles.”
“Check this cross-account trust policy and tell me what looks risky.”

What it gives back to you

You get back a written summary in the chat. It lists the issues Shieldly found, such as wildcards or escalation paths, and explains what each one means. If nothing looks wrong, it tells you that too. You can ask your AI to explain any finding in more detail.

Before you start

What you need

An MCP-compatible AI assistant, such as Claude Desktop, Claude Code, or Cursor
Node.js installed on your computer so the npx command can run
Optional: a Shieldly API key for higher limits (the free demo mode works without one)

Good to know

The free demo mode is rate-limited, so you may hit a cap if you check many policies in a row.

Install it with your AI

Add Shieldly MCP server to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check Shieldly MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.