AWS is a Cloud Platforms MCP server that lets Claude Code, Cursor, Windsurf and any MCP-compatible AI agent official AWS MCP for all AWS services. Install in 1 minute with mcpizy install aws.
Cloud Platforms
Official AWS MCP for all AWS services
Official homepagemcpizy install awsnpx -y @aws/mcp-serverlist_s3_bucketsList S3 buckets in the account
list_s3_objectsList objects in a bucket with a prefix
Inputs
bucketstringrequiredprefixstringoptionalget_s3_objectDownload an S3 object
Inputs
bucketstringrequiredkeystringrequiredlist_ec2_instancesList EC2 instances
Inputs
regionstringoptionalinvoke_lambdaInvoke a Lambda function
Inputs
function_namestringrequiredpayloadobjectoptionalquery_dynamodbQuery a DynamoDB table
Inputs
tablestringrequiredkey_conditionstringrequiredget_cloudwatch_logsFetch CloudWatch log events
Inputs
log_groupstringrequiredWorks identically across clients. Only the config file path differs.
~/.claude.json{
"mcpServers": {
"aws": {
"command": "uvx",
"args": [
"awslabs.aws-api-mcp-server"
],
"env": {
"AWS_REGION": "us-east-1",
"AWS_ACCESS_KEY_ID": "AKIA...",
"AWS_SECRET_ACCESS_KEY": "..."
}
}
}
}.cursor/mcp.json{
"mcpServers": {
"aws": {
"command": "uvx",
"args": [
"awslabs.aws-api-mcp-server"
],
"env": {
"AWS_REGION": "us-east-1",
"AWS_ACCESS_KEY_ID": "AKIA...",
"AWS_SECRET_ACCESS_KEY": "..."
}
}
}
}~/.codeium/windsurf/mcp_config.json{
"mcpServers": {
"aws": {
"command": "uvx",
"args": [
"awslabs.aws-api-mcp-server"
],
"env": {
"AWS_REGION": "us-east-1",
"AWS_ACCESS_KEY_ID": "AKIA...",
"AWS_SECRET_ACCESS_KEY": "..."
}
}
}
}Paste any of these prompts into Claude Code, Cursor or another MCP-compatible client.
“List every S3 bucket and its creation date”
Uses: list_s3_buckets
“Find objects in bucket `my-logs` uploaded today”
Uses: list_s3_objects
“Show me running EC2 instances in eu-west-1”
Uses: list_ec2_instances
“Invoke Lambda `send-report` with payload {date: today}”
Uses: invoke_lambda
If AWS doesn't fit your stack, these Cloud Platforms MCP servers solve similar problems.
The AWS MCP server is an Cloud Platforms Model Context Protocol server that lets Claude Code, Cursor, Windsurf, VS Code with Copilot, and other MCP-compatible AI agents official AWS MCP for all AWS services. It exposes AWS's capabilities as tools the AI can call directly from your editor or CLI.
The fastest way is the MCPizy CLI: run `mcpizy install aws` and MCPizy will add the server to your `.claude.json` automatically. You can also install it manually by adding an entry under `mcpServers` in `.claude.json` with the command `npx -y @aws/mcp-server` and restarting Claude Code.
Yes. The AWS MCP server is free and open source (see the GitHub repository linked on this page). You may still need a AWS account or API key to connect the server to the underlying service, but the MCP layer itself has no MCPizy subscription cost.
Yes. Any MCP-compatible client works — including Claude Code, Claude Desktop, Cursor (via `.cursor/mcp.json`), Windsurf, VS Code with Copilot Chat, and custom agents built on the MCP SDK. The same install command targets all of them; only the config file path differs.
Once installed, your AI agent can official AWS MCP for all AWS services directly inside your conversation. Typical use cases include asking Claude Code or Cursor to run AWS operations, inspect results, chain AWS with other MCP servers (see our Workflow Recipes), and automate repetitive cloud platforms tasks without leaving your editor.