Community MCP server for Amazon Web Services.
uvx mcp-server-aws
{
"mcpServers": {
"aws": {
"env": {
"AWS_REGION": "eu-central-1",
"AWS_ACCESS_KEY_ID": "xxx",
"AWS_SECRET_ACCESS_KEY": "xxx"
},
"args": [
"mcp-server-aws"
],
"command": "uvx"
}
}
}Get CloudWatch metrics
{
"type": "object",
"required": [
"namespace",
"metric_name"
],
"properties": {
"namespace": {
"type": "string"
},
"metric_name": {
"type": "string"
}
}
}// Input
{
"namespace": "AWS/Lambda",
"metric_name": "Invocations"
}// Output
{
"datapoints": [
{
"sum": 1500,
"timestamp": "2026-03-10T12:00:00Z"
}
]
}Query a DynamoDB table
{
"type": "object",
"required": [
"table",
"key_condition"
],
"properties": {
"table": {
"type": "string"
},
"key_condition": {
"type": "string"
}
}
}// Input
{
"table": "users",
"key_condition": "pk = :uid"
}// Output
{
"count": 1,
"items": [
{
"pk": "user1",
"name": "Alice"
}
]
}Invoke an AWS Lambda function
Community MCP server for Amazon Web Services.
AWS provides 4 tools including cloudwatch_get_metrics, dynamodb_query, lambda_invoke, and 1 more.
AWS offers a free tier with 200 calls per month. For higher usage, paid plans start at €0/month.
You can install AWS using the following command: uvx mcp-server-aws. After installation, add the provided config snippet to your Claude Desktop or Cursor configuration.
{
"type": "object",
"required": [
"function_name"
],
"properties": {
"payload": {
"type": "object"
},
"function_name": {
"type": "string"
}
}
}// Input
{
"payload": {
"order_id": 123
},
"function_name": "processOrder"
}// Output
{
"result": {
"processed": true
},
"status_code": 200
}List objects in an S3 bucket
{
"type": "object",
"required": [
"bucket"
],
"properties": {
"bucket": {
"type": "string"
},
"prefix": {
"type": "string"
}
}
}// Input
{
"bucket": "my-data",
"prefix": "uploads/"
}// Output
{
"objects": [
{
"key": "uploads/file.csv",
"size": 1024
}
]
}AWS is listed under the Development Tools category in the AgentForge MCP registry.
AWS has a current uptime of 99.75% with an average response time of 280ms.
To connect AWS, click the "Connect Agent" button on this page to get the configuration snippet. Add it to your MCP client (Claude Desktop, Cursor, or any MCP-compatible tool). Your AI agent will then have access to all of AWS's tools via the Model Context Protocol.