Provides AWS operations for S3 and DynamoDB via MCP with auditable logging.
Configuration
View docs{
"mcpServers": {
"mcp-mirror-rishikavikondala_mcp-server-aws": {
"command": "uv",
"args": [
"--directory",
"/path/to/repo/mcp-server-aws",
"run",
"mcp-server-aws"
],
"env": {
"AWS_REGION": "us-west-2",
"AWS_ACCESS_KEY_ID": "AKIAEXAMPLEKEY",
"AWS_SECRET_ACCESS_KEY": "wJalrXUtnFexample"
}
}
}
}This MCP server provides a Model Context Protocol implementation for AWS operations, enabling you to perform S3 and DynamoDB actions through a unified, auditable interface. It routes requests to AWS services and logs all operations for easy auditing via a dedicated endpoint.
You interact with the AWS MCP Server from an MCP client to perform AWS operations such as creating and listing S3 buckets, uploading and reading objects, and managing DynamoDB tables and items. All actions are automatically logged and can be accessed through the audit endpoint at audit://aws-operations, giving you a clear record of what happened and when.
Prerequisites: you will need the Claude desktop app to run MCP servers locally and an IAM user with read/write permissions for S3 and DynamoDB in your AWS account.
1. Clone the MCP server project into a local directory.
2. Configure your AWS credentials. You can use one of these methods:
- Environment variables: set AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, and AWS_REGION (defaults to us-east-1)
- Default AWS credential chain (set up via AWS CLI with aws configure)
3. Add the MCP server configuration to Claude’s config file. On MacOS, place the file at ~/Library/Application Support/Claude/claude_desktop_config.json. On Windows, place it at %APPDATA%/Claude/claude_desktop_config.json.
"mcpServers": {
"mcp-server-aws": {
"command": "uv",
"args": [
"--directory",
"/path/to/repo/mcp-server-aws",
"run",
"mcp-server-aws"
]
}
}4. Install and open the Claude desktop app.
5. Validate the setup by instructing Claude to perform a read/write operation, such as creating an S3 bucket with a unique name. If you encounter issues, use the debugging tools provided in the MCP guidance to troubleshoot.
Create a new S3 bucket.
List all S3 buckets in your account.
Delete an S3 bucket.
Upload an object to an S3 bucket.
Delete an object from an S3 bucket.
List objects within an S3 bucket.
Read the contents of an object stored in S3.
Create a new DynamoDB table.
Describe details of a DynamoDB table.
Delete a DynamoDB table.
Update a DynamoDB table.
Put an item into a DynamoDB table.
Get an item from a DynamoDB table.
Update an item in a DynamoDB table.
Delete an item from a DynamoDB table.
Query items in a DynamoDB table.
Scan items in a DynamoDB table.
Batch get multiple items from DynamoDB tables.
Batch write operations (put/delete) for DynamoDB items.
Execute multiple PartiQL statements in a batch.
Describe TTL settings for a DynamoDB table.
Update TTL settings for a DynamoDB table.