---
title: "Well-Architected security MCP: review, setup & limitations · Undominated.ai"
canonical: https://undominated.ai/mcp-servers/awslabs-well-architected-security/
description: "AWS Labs MCP server that checks GuardDuty, Security Hub, Inspector, and IAM Access Analyzer and reports Well-Architected security posture without performing remediation itself."
---

# Well-Architected security MCP: review, setup & limitations · Undominated.ai

> AWS Labs MCP server that checks GuardDuty, Security Hub, Inspector, and IAM Access Analyzer and reports Well-Architected security posture without performing remediation itself.

[← Explore all mcp servers](/mcp-servers/)

CLOUD OPERATIONS / AWS Labs

# Well-Architected security MCP

AWS Labs MCP server that checks GuardDuty, Security Hub, Inspector, and IAM Access Analyzer and reports Well-Architected security posture without performing remediation itself.

 [See setup guidance ↓](#setup)[Original source ↗](https://github.com/awslabs/mcp/tree/8840003820a78dd018561d55c7ab12fcdd708464/src/well-architected-security-mcp-server)

SOURCE REVIEW

 Reviewed 2026-10-14
 Evidence 2 linked sources
 Publisher AWS Labs
 Licence [Apache-2.0 ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/LICENSE)
 Revision 8840003820a7
 [Read what was—and wasn’t—checked ↓](#review)

“Names CheckSecurityServices, GetSecurityFindings, AnalyzeSecurityPosture, and ExploreAwsResources, and says remediation belongs in a separate workflow.”

 [AWS Labs · upstream description ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/well-architected-security-mcp-server/README.md) Our analysis follows below.

01 / THE REASONING

## Why this made the selection.

 - The catalogue's AWS security coverage is CloudTrail and related operations servers, not this Well-Architected security assessment server.
- The README says automated remediation should stay in another workflow.

### A good fit for

 - Checking whether GuardDuty, Security Hub, Inspector, and IAM Access Analyzer are enabled
- Reading security findings for an operations review

### Weigh up before choosing

 - This review did not execute it.
- This review did not install the package or start the server.
- The server directory has no LICENSE file; the repository root LICENSE at the same commit is the Apache-2.0 file cited.
- The README does not say stdio or http in the portion reviewed, so no transport is recorded.

02 / THE REVIEW RECORD

## What we actually inspected.

Source review has boundaries. A clear record is more useful than a “safe” badge.

### Material inspected

 - src/well-architected-security-mcp-server/README.md
- LICENSE

### Our findings

 - The features section names GuardDuty, Security Hub, Inspector, and IAM Access Analyzer status, plus findings, resource discovery, and storage and network encryption checks.
- It names CheckSecurityServices, GetSecurityFindings, AnalyzeSecurityPosture, and ExploreAwsResources.
- It says automated remediation should be implemented through separate operational workflows. A directory LICENSE returned HTTP 404, and the root LICENSE is Apache-2.0.

### Not established by this review

 - The server was not started.
- No AWS security API was called.
- The package was not installed.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

## Connect a server deliberately.

[Upstream setup instructions ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/well-architected-security-mcp-server/README.md)

DOCUMENTED COMMAND

 uv pip install awslabs.well-architected-security-mcp-server Copy command ↗

Copying does not execute this command. It may retrieve a newer version than the reviewed source.

 - The README shows that uv command and, on the next line, pip install awslabs.well-architected-security-mcp-server.
- AWS credentials are required to query the services and were not configured here.

### Before you start

 - uv or pip
- AWS credentials that can read the named security services

### Compatibility

MCP clients that can launch the installed package

### Implementation

python

### Read AWS security posture

 - Read security service status and findings
- Inventory resources for the assessment
- Does not remediate findings inside this server

### Cost model

Apache-2.0 at the awslabs/mcp root; AWS account access is required to query findings

04 / FOLLOW THE EVIDENCE

## The source trail.

Our notes are separate from the original resource. Check upstream before adopting a new version.

 - [Well-Architected security README ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/well-architected-security-mcp-server/README.md) Checked 2026-10-14 https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/well-architected-security-mcp-server/README.md Supports: tool names and remediation limit
- [Repository root LICENSE ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/LICENSE) Checked 2026-10-14 https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/LICENSE Supports: Apache-2.0; directory LICENSE was absent

KEEP COMPARING

## Other approaches to consider.

Related by category or shared topics. These are alternatives to inspect, not a measured quality order.

 [### AWS Billing and Cost Management MCP Server ↗ Reads realised AWS billing and cost-management data, which is a different number from the advertised unit price.](/mcp-servers/awslabs-aws-billing-cost-management/)[### AWS CloudTrail MCP Server ↗ Queries CloudTrail events for an account you administer.](/mcp-servers/awslabs-cloudtrail/)[### AWS CloudWatch Application Signals MCP Server ↗ Reads CloudWatch Application Signals for an account you administer. It is not the general CloudWatch server.](/mcp-servers/awslabs-cloudwatch-applicationsignals/)

 [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/)

## Continue your investigation

 - [Inspect resource evidence](/tools/)
- [Choose a host](/agents/)
- [Inspect reusable workflows](/skills/)
- [Use Undominated data](/api/)
