AWS Operations MCP Server

Cloud PlatformsPython

Manage AWS resources like S3 and DynamoDB directly through Claude

Available Tools

s3_bucket_create

Create a new S3 bucket

s3_bucket_list

List all S3 buckets

s3_bucket_delete

Delete an S3 bucket

s3_object_upload

Upload an object to S3

s3_object_delete

Delete an object from S3

s3_object_list

List objects in an S3 bucket

s3_object_read

Read an object's content from S3

dynamodb_table_create

Create a new DynamoDB table

dynamodb_table_describe

Get details about a DynamoDB table

dynamodb_table_delete

Delete a DynamoDB table

dynamodb_table_update

Update a DynamoDB table

dynamodb_item_put

Put an item into a DynamoDB table

dynamodb_item_get

Get an item from a DynamoDB table

dynamodb_item_update

Update an item in a DynamoDB table

dynamodb_item_delete

Delete an item from a DynamoDB table

dynamodb_item_query

Query items in a DynamoDB table

dynamodb_item_scan

Scan items in a DynamoDB table

dynamodb_batch_get

Batch get multiple items from DynamoDB tables

dynamodb_item_batch_write

Batch write operations (put/delete) for DynamoDB items

dynamodb_batch_execute

Execute multiple PartiQL statements in a batch

dynamodb_describe_ttl

Get the TTL settings for a table

dynamodb_update_ttl

Update the TTL settings for a table

AWS Operations is a Model Context Protocol server that enables Claude to interact directly with AWS services. It currently supports comprehensive operations for S3 and DynamoDB, allowing you to create, read, update, and delete resources without leaving your conversation. All operations performed through this server are automatically logged and can be accessed through the audit trail, providing transparency and accountability for AWS resource management. This server bridges the gap between conversational AI and cloud infrastructure management.

Overview

AWS Operations is a Model Context Protocol server that allows Claude to interact with AWS services directly. With this server, you can manage S3 buckets and objects, as well as perform a wide range of DynamoDB operations, all through natural language requests to Claude.

Installation

Prerequisites

Before installing the AWS Operations server, you need to:

Have an AWS account with appropriate permissions for S3 and DynamoDB
Set up your AWS credentials using one of these methods:
- Environment variables: AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, and AWS_REGION (defaults to us-east-1)
- AWS credential chain (configured via AWS CLI with aws configure)
- AWS profile (set the AWS_PROFILE environment variable)

Installation Options

Option 1: Install via Smithery (Recommended)

The easiest way to install AWS Operations is through Smithery:

npx -y @smithery/cli install mcp-server-aws --client claude

Option 2: Manual Installation

Clone the repository:

git clone https://github.com/rishikavikondala/mcp-server-aws.git

Navigate to the repository directory:
```
cd mcp-server-aws
```
Install dependencies (using uv):
```
uv pip install -e .
```
Add the server configuration to your Claude Desktop config file:
- On macOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
- On Windows: %APPDATA%/Claude/claude_desktop_config.json
Add the following to your configuration file:
```
"mcpServers": {
  "mcp-server-aws": {
    "command": "uv",
    "args": [
      "--directory",
      "/path/to/repo/mcp-server-aws",
      "run",
      "mcp-server-aws"
    ]
  }
}
```
Replace /path/to/repo/mcp-server-aws with the actual path to the cloned repository.

Option 3: Using Docker

You can also run the server using Docker:

Build the Docker image:
```
docker build -t mcp-server-aws .
```

Run the container with your AWS credentials:

docker run -p 8000:8000 \
  -e AWS_ACCESS_KEY_ID=your_access_key \
  -e AWS_SECRET_ACCESS_KEY=your_secret_key \
  -e AWS_REGION=your_region \
  mcp-server-aws

Usage

Once installed, you can ask Claude to perform AWS operations. Here are some example prompts:

"Create a new S3 bucket called 'my-test-bucket'"
"List all my S3 buckets"
"Upload a text file to my S3 bucket with the content 'Hello, World!'"
"Create a new DynamoDB table with a primary key 'id'"
"Add an item to my DynamoDB table"
"Query my DynamoDB table for items matching a specific condition"

All operations performed through the server are automatically logged and can be accessed through the audit://aws-operations resource endpoint.

Troubleshooting

If you encounter issues:

Verify your AWS credentials are correctly set up
Check that the Claude Desktop app is properly configured with the server
Ensure you have the necessary permissions in your AWS account
Use the MCP debugging tools available in the Claude Desktop app

For more detailed troubleshooting, refer to the Model Context Protocol debugging documentation.