AWS MCP enables Claude and other AI assistants to query and manage AWS resources through natural language conversations by integrating with the Model Context Protocol. The server provides tools for discovering and modifying EC2 instances, S3 buckets, Lambda functions, ECS clusters, and other AWS services across multiple regions and profiles while maintaining secure credential handling through local AWS credentials. This solves the problem of requiring manual AWS console navigation or CLI commands by allowing seamless resource management directly within Claude conversations.
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 alternative.

~/.aws/ directory)git clone https://github.com/RafalWilinski/aws-mcp
cd aws-mcp
pnpm install
# or
npm install

claude_desktop_config.json:{
"mcpServers": {
"aws": {
"command": "npm", // OR pnpm
"args": [
"--silent",
"--prefix",
"/Users/<YOUR USERNAME>/aws-mcp",
"start"
]
}
}
}
Important: Replace /Users/<YOUR USERNAME>/aws-mcp with the actual path to your project directory.

nvmBuild from source first and add following config:
{
"mcpServers": {
"aws": {
"command": "/Users/<USERNAME>/.nvm/versions/node/v20.10.0/bin/node",
"args": [
"<WORKSPACE_PATH>/aws-mcp/node_modules/tsx/dist/cli.mjs",
"<WORKSPACE_PATH>/aws-mcp/index.ts",
"--prefix",
"<WORKSPACE_PATH>/aws-mcp",
"start"
]
}
}
}
To see logs:
tail -n 50 -f ~/Library/Logs/Claude/mcp-server-aws.log
# or
tail -n 50 -f ~/Library/Logs/Claude/mcp.log
silenceper/mcp-k8s
azure/containerization-assist
io.github.evozim/aws-builder
reza-gholizade/k8s-mcp-server
flux159/mcp-server-kubernetes