INFRASTRUCTURE VALIDATION / AWS Labs
AWS IaC MCP Server
Validates CloudFormation templates, retrieves CDK/CloudFormation guidance and investigates failed deployments.
“Get started with this MCP server for creating and troubleshooting AWS infrastructure as code.”
01 / THE REASONING
Why this made the selection.
- Combines template validation and compliance checks with source documentation for the same infrastructure workflow.
- The inspected tool definitions distinguish local template checks from account-backed deployment troubleshooting.
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/aws-iac-mcp-server/README.md (installation, capability and permission sections)
- src/aws-iac-mcp-server/pyproject.toml
- src/aws-iac-mcp-server/awslabs/aws_iac_mcp_server/server.py
- LICENSE
- src/aws-iac-mcp-server/awslabs/aws_iac_mcp_server/client/aws_knowledge_client.py
Our findings
- The server registers validation, compliance, troubleshooting and documentation tools; a resource deployment/apply tool was not established.
- The current package is awslabs.aws-iac-mcp-server; obsolete CDK/Cloud Control entries should not be substituted.
- server.py registers validate_cloudformation_template, check_cloudformation_template_compliance, troubleshoot_cloudformation_deployment, get_cloudformation_pre_deploy_validation_instructions, search_cdk_documentation, search_cloudformation_documentation, search_cdk_samples_and_constructs and cdk_best_practices. It also proxies read_iac_documentation_page from the remote AWS Knowledge MCP tool aws___read_documentation.
- Documentation search and page reads go to the AWS Knowledge MCP endpoint, https://knowledge-mcp.global.api.aws unless KNOWLEDGE_MCP_ENDPOINT overrides it.
- troubleshoot_cloudformation_deployment takes a stack name and region, and adds CloudTrail analysis unless include_cloudtrail is false.
- The README’s client block launches uvx awslabs.aws-iac-mcp-server@latest with AWS_PROFILE set to your-named-profile and FASTMCP_LOG_LEVEL ERROR.
Not established by this review
- Server startup, authentication and tool execution were not tested.
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.
DOCUMENTED COMMAND
uvx awslabs.aws-iac-mcp-server@latest Copying does not execute this command. It may retrieve a newer version than the reviewed source.
- Add the documented stdio configuration to the client.
- Set the intended AWS profile when using live-account troubleshooting; provide template text for validation tools.
- The one-line command above is the uvx launch in the README client block at this commit, not a separate installer. It was not run.
Before you start
- uv/Python; AWS credentials for tools that inspect account resources.
Documented configuration example
Use the client and authentication context described in the setup guidance. Configuration formats vary between hosts.
{
"mcpServers": {
"awslabs.aws-iac-mcp-server": {
"command": "uvx",
"args": [
"awslabs.aws-iac-mcp-server@latest"
],
"env": {
"AWS_PROFILE": "your-named-profile",
"FASTMCP_LOG_LEVEL": "ERROR"
},
"disabled": false,
"autoApprove": []
}
}
} 04 / FOLLOW THE EVIDENCE
The source trail.
Our notes are separate from the original resource.
Check upstream before adopting a new version.
- Official documentation ↗Checked
https://github.com/awslabs/mcp/blob/e1abc4b3b16a6da4c86ccbfc89de7bd864c5679e/src/aws-iac-mcp-server/README.md
Supports: summary, whySelected, bestFor, limitations, install, access, compatibility, transports, configExample, review
- Applicable source licence ↗Checked
https://github.com/awslabs/mcp/blob/e1abc4b3b16a6da4c86ccbfc89de7bd864c5679e/LICENSE
Supports: license
https://github.com/awslabs/mcp/blob/e1abc4b3b16a6da4c86ccbfc89de7bd864c5679e/src/aws-iac-mcp-server/pyproject.toml
Supports: language, review
https://github.com/awslabs/mcp/blob/e1abc4b3b16a6da4c86ccbfc89de7bd864c5679e/src/aws-iac-mcp-server/awslabs/aws_iac_mcp_server/server.py
Supports: language, review, Tool list
https://github.com/awslabs/mcp/blob/e1abc4b3b16a6da4c86ccbfc89de7bd864c5679e/src/aws-iac-mcp-server/awslabs/aws_iac_mcp_server/client/aws_knowledge_client.py
Supports: review, access, AWS Knowledge MCP endpoint default