What is Aws Storage Mcp

aws-storage-mcp is a Model Context Protocol (MCP) server that facilitates natural language interactions with AWS storage services through the Amazon Q CLI, allowing users to manage and query their storage resources effortlessly.

Use cases

Use cases for aws-storage-mcp include querying AWS storage resources like S3 buckets, performing operations without remembering complex commands, obtaining information about storage resources conversationally, and managing multiple storage services from a single interface.

How to use

To use aws-storage-mcp, set up the server and connect it to your AWS account. You can then interact with AWS storage services using natural language queries via the Amazon Q CLI, simplifying complex operations.

Key features

Key features of aws-storage-mcp include a natural language interface for AWS services, simplified workflows for performing operations, contextual understanding for domain-specific queries, extended capabilities without the need for model retraining, and local execution of commands using user credentials.

Where to use

aws-storage-mcp can be used in various domains such as cloud computing, data management, and IT operations, where users need to interact with AWS storage services efficiently.

AWS Storage MCP Server

A Model Context Protocol (MCP) server that enables natural language interactions with AWS storage services through Amazon Q CLI.

Disclaimer

This project is provided “as is” without warranty of any kind, express or implied. The authors and contributors are not responsible for any damages or liabilities that may arise from using this software.

• Not an Official AWS Product: This is a community project and is not officially supported by Amazon Web Services.
• Use at Your Own Risk: Review all operations before executing them, especially those that modify or delete resources.
• Cost Implications: Using AWS services may incur costs to your AWS account. You are responsible for monitoring and managing these costs.
• Security Considerations: This tool requires AWS credentials to function. Always follow security best practices when handling credentials.
• No Liability: The authors and contributors cannot be held liable for any data loss, unexpected charges, or other damages resulting from the use of this software.

What is MCP?

The Model Context Protocol (MCP) is an open protocol that standardizes how applications provide context to Large Language Models (LLMs). MCP enables communication between LLMs like Amazon Q and locally running MCP servers that provide additional tools and capabilities.

Why Use MCP?

• Natural Language Interface: Interact with AWS services using plain English instead of complex CLI commands
• Simplified Workflows: Perform complex operations with simple queries like “list my S3 buckets”
• Contextual Understanding: MCP servers provide domain-specific knowledge to LLMs
• Extended Capabilities: Add new functionalities to your LLM without retraining the model
• Local Execution: Operations execute on your local machine with your credentials

What This Project Does

This AWS Storage MCP server connects Amazon Q to your AWS storage services, allowing you to:

1. Query AWS storage resources using natural language
2. Perform operations on AWS storage services without remembering complex commands
3. Get information about your storage resources in a conversational manner
4. Manage multiple storage services from a single interface

Architecture Diagram

Supported AWS Storage Services

• Amazon S3: Object storage for any type of data
• Amazon EBS: Block storage for EC2 instances
• Amazon EFS: Scalable file storage for EC2 instances
• Amazon FSx: Fully managed file storage built on Windows Server
• AWS Storage Gateway: Hybrid cloud storage that connects on-premises environments with cloud storage
• Amazon S3 Glacier: Low-cost archive storage
• AWS Snow Family: Physical devices for data migration and edge computing
• AWS Backup: Centralized backup service
• Amazon S3 Object Lambda: Process S3 data during retrieval
• Amazon S3 Glacier Deep Archive: Lowest-cost archive storage class

Prerequisites

• Docker and Docker Compose
• AWS CLI configured with valid credentials
• Amazon Q CLI installed

Quick Start

• For detailed installation instructions, please refer to the Installation Guide.
• For detailed usage examples, please refer to the Usage Guide.
• For practical examples and demonstrations, see the Examples Guide.

Troubleshooting

If you encounter issues:

1. Check Docker Container Status

   docker ps | grep aws-storage
   

2. View Container Logs

   docker logs aws-storage-mcp-aws-storage-mcp-1
   

3. Test the API Directly

   curl -s -X POST -H "Content-Type: application/json" -d '{"tool_name": "list_aws_profiles", "parameters": {}}' http://localhost:8080/invoke
   

4. Verify AWS Credentials
   Make sure your AWS credentials are valid and have the necessary permissions.

5. Restart the Container

   docker compose restart
   

Project Structure

aws-storage-mcp/
├── README.md               # This documentation
├── requirements.txt        # Python dependencies
├── mcp-manifest.json       # MCP server manifest
├── docker-compose.yml      # Docker configuration
├── docker-compose.override.yml # Volume mapping for AWS credentials
├── Dockerfile              # Docker build instructions
├── setup.sh                # Environment setup script
├── start-docker.sh         # Server startup script
└── src/                    # Source code
    ├── server.py           # MCP server implementation
    └── services/           # AWS service modules
        ├── __init__.py
        ├── base.py         # Base service class
        ├── s3.py           # S3 operations
        ├── ebs.py          # EBS operations
        ├── efs.py          # EFS operations
        └── ...             # Other service modules

Documentation

• Installation Guide - Detailed installation instructions
• Usage Guide - Examples and usage instructions
• Contributing Guide - How to contribute to this project
• Code of Conduct - Community guidelines

Contributing

Contributions are welcome! Please read our Contributing Guide for details on how to submit pull requests, report issues, and suggest enhancements.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Security Notes

• This MCP server runs with your AWS credentials
• All operations are executed with your permissions
• Review the code before running in production environments
• Consider using IAM roles with least privilege principles