A lightweight MCP server that enables AI assistants like Claude to execute AWS CLI commands in a safe containerized environment.
AWS MCP Server is a Model Context Protocol (MCP) server that bridges AI assistants like Claude with AWS infrastructure management. It provides AI tools with direct access to all 200+ AWS services by wrapping the AWS CLI, enabling natural language interaction with cloud resources. This approach simplifies cloud operations by allowing AI to learn and execute AWS commands on-demand within secure, IAM-controlled boundaries.
Developers, DevOps engineers, and cloud administrators who use AI coding assistants (like Claude) and need to manage AWS infrastructure through natural language. It is specifically for teams integrating MCP-aware tools into their AWS workflows.
Developers choose this over building custom API wrappers because it leverages the existing AWS CLI to provide immediate, comprehensive access to all AWS services without reinventing the wheel. Its unique layered security model combines IAM policies, configurable sandboxing, and Docker isolation for safe execution.
A lightweight service that enables AI assistants to execute AWS CLI commands (in safe containerized environment) through the Model Context Protocol (MCP). Bridges Claude, Cursor, and other MCP-aware AI tools with AWS CLI for enhanced cloud infrastructure management.
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
Wraps the entire AWS CLI to provide immediate access to all 200+ AWS services without building custom API wrappers, as highlighted in the README's philosophy section.
The aws_cli_help tool allows AI assistants to retrieve documentation on-demand, enabling adaptive learning and execution of AWS commands, which simplifies cloud operations.
Combines IAM policies as the primary boundary with configurable sandboxing and Docker isolation for enhanced safety, as detailed in the Security documentation.
Supports stdio and streamable-http transports for compatibility with various MCP clients, including web-based tools, though SSE is deprecated.
Requires AWS CLI installation and configuration, adding setup overhead and potential version conflicts, which can be a barrier for teams not already using it.
Security hinges on properly configured IAM policies; setting up least-privilege access is non-trivial and error-prone, risking overprivileged execution if misconfigured.
Enforces a maximum output of 100,000 characters via AWS_MCP_MAX_OUTPUT, which may truncate large AWS responses and affect data completeness in AI interactions.