AWS MCP
A Model Context Protocol (MCP) server that enables AI assistants like Claude to interact with your AWS environment. This allows for natural language querying and management of your AWS resources during conversations. Think of better Amazon Q alternat
What is AWS MCP?
AWS MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context protocol (mcp) server that enables ai assistants like claude to interact with your aws environment. this allows for natural language querying and management of your aws resources during ...
A Model Context Protocol (MCP) server that enables AI assistants like Claude to interact with your AWS environment. This allows for natural language querying and management of your AWS resources during conversations. Think of better Amazon Q alternat
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A Model Context Protocol (MCP) server that enables AI assist
Use Cases
Maintainer
Works with
Installation
NPM
npx -y awsManual Installation
npx -y awsConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use AWS MCP
The aws-mcp server is a Model Context Protocol server that gives Claude and other MCP clients natural language access to your AWS environment, enabling you to query and manage EC2 instances, S3 buckets, Lambda functions, ECS clusters, and other AWS resources through conversation. It uses your locally configured AWS credentials (profiles and regions) so no secrets are ever sent to external services. It positions itself as a more conversational alternative to Amazon Q, letting you ask questions like 'What Lambda functions are deployed in us-east-1?' and get structured answers.
Prerequisites
- Node.js 18 or later and npm or pnpm installed
- AWS CLI configured with valid credentials (run 'aws configure' or use ~/.aws/credentials and ~/.aws/config)
- At least one AWS profile with permissions to describe/list the resources you want to query
- Claude Desktop or another MCP-compatible client
Clone the aws-mcp repository
The server is not published to npm under a usable package name for MCP purposes, so clone and build it locally.
git clone https://github.com/RafalWilinski/aws-mcp
cd aws-mcp
npm installVerify your AWS credentials are configured
The server inherits credentials from the standard AWS credential chain. Confirm at least one profile is active.
aws sts get-caller-identityAdd the server to Claude Desktop config
Edit claude_desktop_config.json to register the aws-mcp server, replacing USERNAME with your actual macOS username and adjusting the path to where you cloned the repo.
{
"mcpServers": {
"aws": {
"command": "npm",
"args": ["--silent", "--prefix", "/Users/USERNAME/aws-mcp", "start"]
}
}
}Restart Claude Desktop
Quit and relaunch Claude Desktop to pick up the new server configuration. The AWS tools should now appear in the tool list.
Ask Claude to list your AWS resources
Start with a simple query to confirm the server is working and your credentials are being picked up correctly.
AWS MCP Examples
Client configuration
Claude Desktop config pointing to a locally cloned aws-mcp repository.
{
"mcpServers": {
"aws": {
"command": "npm",
"args": ["--silent", "--prefix", "/Users/USERNAME/aws-mcp", "start"]
}
}
}Prompts to try
Natural language prompts for querying and managing AWS resources through Claude.
- "List all my AWS profiles and which regions are configured for each."
- "Show me all EC2 instances in us-east-1 and their current state."
- "List all S3 buckets in my account along with their approximate sizes."
- "What Lambda functions are deployed in eu-west-1 and when were they last modified?"
- "List all ECS clusters and show the services running in each cluster."Troubleshooting AWS MCP
Claude cannot see any AWS resources
Run 'aws sts get-caller-identity' in your terminal to confirm credentials are valid and the correct profile is active. The MCP server uses the default profile unless AWS_PROFILE is set in the environment block of your MCP config.
Server fails to start with 'Cannot find module' error
Run 'npm install' inside the cloned aws-mcp directory to install dependencies before registering the server. The npm --prefix flag does not install packages—it only sets the working directory for the start script.
Multi-region queries only return results from one region
Specify the region explicitly in your prompt (e.g. 'in us-west-2'). The server supports multi-region queries but may default to the region in your active AWS profile if none is specified.
Frequently Asked Questions about AWS MCP
What is AWS MCP?
AWS MCP is a Model Context Protocol (MCP) server that model context protocol (mcp) server that enables ai assistants like claude to interact with your aws environment. this allows for natural language querying and management of your aws resources during conversations. think of better amazon q alternat It connects AI assistants to external tools and data sources through a standardized interface.
How do I install AWS MCP?
Install via npm with the command: npx -y aws. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with AWS MCP?
AWS MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is AWS MCP free to use?
Yes, AWS MCP is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
AWS MCP Alternatives — Similar Cloud Services Servers
Looking for alternatives to AWS MCP? 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 MCP 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 MCP?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.