AWS
A read-only Model Context Protocol server that exposes over 60 AWS tools across services like EC2, S3, and IAM for AI agent interaction. It features multi-region support, resource caching, and audit logging to provide secure, AI-ready access to AWS i
What is AWS?
AWS is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to read-only model context protocol server that exposes over 60 aws tools across services like ec2, s3, and iam for ai agent interaction. it features multi-region support, resource caching, and audit log...
A read-only Model Context Protocol server that exposes over 60 AWS tools across services like EC2, S3, and IAM for AI agent interaction. It features multi-region support, resource caching, and audit logging to provide secure, AI-ready access to AWS i
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A read-only Model Context Protocol server that exposes over
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx aws-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use AWS
The AWS MCP Server is a read-oriented Model Context Protocol server that exposes over 60 tools across core AWS services including S3, DynamoDB, EC2, and IAM, making them accessible to AI agents via natural language. It features multi-region support, resource caching, and a built-in audit log resource so every operation is traceable. Teams use it to let AI assistants query and manage cloud infrastructure, automate routine AWS tasks, and answer questions about existing resources without writing custom scripts.
Prerequisites
- Python 3.10+ or Node.js 18+ depending on your chosen runner
- AWS account with IAM credentials (AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY)
- AWS CLI configured, or credentials set via environment variables
- An MCP-compatible client such as Claude Desktop
- Git to clone the repository
Install via Smithery (automated)
The quickest way to install is through Smithery, which handles configuration automatically for Claude Desktop.
npx -y @smithery/cli install mcp-server-aws --client claudeConfigure AWS credentials
The server authenticates to AWS using standard credential environment variables. Set these in your shell or directly in the MCP client configuration.
export AWS_ACCESS_KEY_ID=your_access_key_id
export AWS_SECRET_ACCESS_KEY=your_secret_access_key
export AWS_REGION=us-east-1Clone the repository for manual setup
If not using Smithery, clone the repository and install dependencies manually.
git clone https://github.com/rishikavikondala/mcp-server-aws.git
cd mcp-server-aws
pip install -r requirements.txtAdd the server to your MCP client configuration
Edit your Claude Desktop config file to register the server. On macOS this is at ~/Library/Application Support/Claude/claude_desktop_config.json.
{
"mcpServers": {
"aws": {
"command": "python",
"args": ["/path/to/mcp-server-aws/server.py"],
"env": {
"AWS_ACCESS_KEY_ID": "your_access_key_id",
"AWS_SECRET_ACCESS_KEY": "your_secret_access_key",
"AWS_REGION": "us-east-1"
}
}
}
}Verify the connection
Restart Claude Desktop and ask it to perform a simple read operation, such as listing your S3 buckets, to confirm the server is connected and credentials are working.
AWS Examples
Client configuration
Full claude_desktop_config.json entry for the AWS MCP Server with credentials passed as environment variables.
{
"mcpServers": {
"aws": {
"command": "python",
"args": ["/path/to/mcp-server-aws/server.py"],
"env": {
"AWS_ACCESS_KEY_ID": "AKIAIOSFODNN7EXAMPLE",
"AWS_SECRET_ACCESS_KEY": "wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY",
"AWS_REGION": "us-east-1"
}
}
}
}Prompts to try
These natural language prompts work once Claude is connected to the AWS MCP Server.
- "List all my S3 buckets and their regions"
- "Show me all DynamoDB tables in us-west-2"
- "Create a new S3 bucket named my-test-bucket-12345 in us-east-1"
- "Query the Orders DynamoDB table for items where status equals pending"
- "Show me the recent audit log of all AWS operations performed"Troubleshooting AWS
Authentication errors when calling AWS tools
Verify that AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY are correctly set in the env block of your MCP config, and that the IAM user has the appropriate permissions for the services you're querying.
Operations fail for resources in a different region than AWS_REGION
The server supports multi-region access. Specify the target region explicitly in your prompt (e.g., 'list S3 buckets in eu-west-1') or change the AWS_REGION environment variable to match the region of your resources.
Frequently Asked Questions about AWS
What is AWS?
AWS is a Model Context Protocol (MCP) server that read-only model context protocol server that exposes over 60 aws tools across services like ec2, s3, and iam for ai agent interaction. it features multi-region support, resource caching, and audit logging to provide secure, ai-ready access to aws i It connects AI assistants to external tools and data sources through a standardized interface.
How do I install AWS?
Follow the installation instructions on the AWS GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with AWS?
AWS works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is AWS free to use?
Yes, AWS is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
AWS Alternatives — Similar Cloud Services Servers
Looking for alternatives to AWS? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up AWS in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use AWS?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.