Aws Sage MCP Server

A production-grade [Model Context Protocol (MCP)](https://modelcontextprotocol.io) server for AWS. Connect AI assistants to your AWS infrastructure

Local serverstdioPython

What is the Aws Sage MCP Server?

A production-grade Model Context Protocol (MCP) server for AWS. Connect AI assistants to your AWS infrastructure and manage it

What it needs from you

  • Python 3.11+ - AWS credentials configured (~/.aws/credentials or ~/.aws/config) - Any MCP-compatible client (see Compatible Clients above)

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

Recorded tools

Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.

ToolWhat it does
list_profilesList available AWS profiles
select_profileSelect and authenticate with a profile
get_account_infoShow current account ID, region, identity
set_safety_modeSwitch between READ_ONLY, STANDARD, UNRESTRICTED
aws_queryNatural language AWS queries
validate_operationCheck if an operation is valid without executing
aws_executeExecute validated AWS operations
get_contextView conversation context and recent resources
set_aliasCreate shortcuts for resources (e.g., "prod-db")
list_aliasesView all defined aliases
discover_resourcesFind resources by tags across all services
map_dependenciesShow what a resource depends on
impact_analysisPredict what breaks if you modify/delete something
investigate_incidentAutomated incident investigation workflows
search_docsSearch AWS documentation
get_aws_knowledgeQuery built-in AWS knowledge base
get_best_practicesGet service-specific best practices
get_service_limitsShow default service quotas
find_idle_resourcesFind unused EC2/RDS/EBS/EIP resources
get_rightsizing_recommendationsGet EC2 right-sizing suggestions
get_cost_breakdownSpending analysis by service/tag
project_costsEstimate costs before deployment
list_environmentsList configured environments (production/localstack)
switch_environmentSwitch between LocalStack and production
get_environment_infoCurrent environment details
check_localstackVerify LocalStack connectivity
compare_environmentsDiff resources between environments
assume_roleAssume role in another account via STS
list_accountsShow configured accounts
switch_accountChange active account context

How to install the Aws Sage MCP Server

{
  "mcpServers": {
    "aws-sage": {
      "command": "/path/to/python3",
      "args": [
        "-m",
        "aws_sage.server"
      ],
      "env": {
        "AWS_PROFILE": "default"
      }
    }
  }
}

From the project documentation. Replace placeholders and example paths before connecting.

Configuration

  • Python 3.11+ - AWS credentials configured (~/.aws/credentials or ~/.aws/config) - Any MCP-compatible client (see Compatible Clients above)
VariableDescriptionRequired
AWS_PROFILEDeclared in the maintainer’s client configuration.Check documentation

Example prompts to try

  • “Use Aws Sage to Prerequisites.”
  • “Use Aws Sage to Cursor.”
  • “Use Aws Sage to Windsurf.”

Frequently asked questions

A production-grade [Model Context Protocol (MCP)](https://modelcontextprotocol.io) server for AWS. Connect AI assistants to your AWS infrastructure and manage it Confirm the tools offered by your installed version in the connected client. Tool availability and permissions depend on the server and account configuration.