What is an MCP Server?

An MCP (Model Context Protocol) server acts as a bridge, allowing AI models to access and interact with external data sources and tools. It standardizes how applications provide context to LLMs.

Why should I use the MCP Server for AWS SSO?

This server provides a secure and seamless way for AI systems to interact with AWS resources using temporary credentials, avoiding the risks associated with long-term credentials. It simplifies authentication, supports multi-account management, and is compatible with the AWS CLI.

What are the prerequisites for using this server?

You need Node.js (>=18.x), AWS CLI v2, and an AWS account with SSO configured.

How do I configure the AWS SSO Start URL?

You can configure the AWS SSO Start URL either through an MCP config file (~/.mcp/configs.json) or by setting environment variables (AWS_SSO_START_URL).

What MCP tools are available?

The MCP Server provides the following tools:

• aws_sso_login: Initiates AWS SSO device authorization.
• aws_sso_status: Checks SSO authentication status.
• aws_sso_ls_accounts: Lists accessible AWS accounts/roles.
• aws_sso_exec_command: Executes AWS CLI command with temporary credentials.
• aws_sso_ec2_exec_command: Runs shell commands on EC2 via SSM.

How do I execute AWS CLI commands using this server?

You can use the aws_sso_exec_command MCP tool or the exec-command CLI command. You need to specify the account ID, role name, and the command to execute.

What is the response format?

All responses are Markdown-formatted and include the status, context (account, role, region, execution time), and the command output or troubleshooting steps.

How do I contribute to this project?

Fork the repository, create a feature branch, commit your changes, push to the branch, and open a pull request. See CONTRIBUTING.md for more details.