Spark
Sign In
MCP Connector

Manage AWS S3 and DynamoDB with MCP

MCP server for AWS S3 and DynamoDB - buckets, objects, tables, items, batch operations, and TTL, with every call audit-logged.

Connect
Works with awss3dynamodb
Rishi Kavikondala
Own this? Claim it

Maintainer of this project? Claim this page to edit the listing.

90
Spark score
out of 100
Updated Apr 2025
Fresher alternatives ↓
Version 1.0.0
Models
universal
Add to Favorites

Why it matters

Integrate with AWS services like S3 and DynamoDB using the Model Context Protocol. Automate bucket and table management, object operations, and item manipulation with built-in logging and auditing.

Outcomes

What it gets done

01

Create, list, and delete S3 buckets and objects.

02

Manage DynamoDB tables, including creation, description, and deletion.

03

Perform item operations (put, get, update, delete) on DynamoDB tables.

04

Enable automatic operation logging and access an audit trail for AWS actions.

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/vb-aws | bash

Capabilities

Tools your agent gets

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 the contents of an object from S3

dynamodb_table_create

Create a new DynamoDB table

+7 tools

Overview

AWS MCP Server

An MCP server exposing S3 and DynamoDB read/write operations - buckets, objects, tables, items, batch operations, and TTL - with automatic audit logging. Use when an assistant needs to manage S3 storage or DynamoDB data directly, given an IAM user scoped to those services.

What it does

AWS MCP Server gives an assistant direct read/write access to Amazon S3 and DynamoDB. Every operation it performs is automatically logged and retrievable through the audit://aws-operations resource endpoint, giving a built-in audit trail of everything the assistant did against the AWS account.

When to use - and when NOT to

Use this connector when an assistant needs to manage S3 buckets and objects or DynamoDB tables and items conversationally - creating a bucket, uploading or reading an object, querying or scanning a DynamoDB table, or adjusting TTL settings. It requires an IAM user with read/write permissions scoped to S3 and DynamoDB, so its blast radius is exactly those two services; because writes and deletes execute for real against the connected AWS account, it is worth confirming actions like bucket or table deletion before letting the assistant run them autonomously, especially given the automatic audit logging exists precisely because these operations are consequential.

Capabilities

S3 tools cover the full bucket and object lifecycle: s3_bucket_create, s3_bucket_list, s3_bucket_delete, s3_object_upload, s3_object_delete, s3_object_list, and s3_object_read. DynamoDB tools span four groups: table operations (dynamodb_table_create, _describe, _delete, _update), item operations (dynamodb_item_put, _get, _update, _delete, _query, _scan), batch operations (dynamodb_batch_get, dynamodb_item_batch_write, and dynamodb_batch_execute for running multiple PartiQL statements at once), and TTL operations (dynamodb_describe_ttl, dynamodb_update_ttl).

How to install

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

for automatic Smithery install, or manually: clone the repository, provide AWS credentials either via AWS_ACCESS_KEY_ID/AWS_SECRET_ACCESS_KEY/AWS_REGION (default us-east-1) environment variables or the default AWS credential chain (aws configure), then add it to claude_desktop_config.json as a uv run mcp-server-aws command pointed at the cloned directory. Verify the setup by asking Claude to perform a simple read/write operation, such as creating an S3 bucket with a random name.

Who it's for

Developers and cloud engineers who want an assistant to manage S3 storage and DynamoDB data directly - creating buckets and tables, uploading and querying data, running batch PartiQL statements, or adjusting TTL policies - with every operation logged for auditability, rather than scripting AWS SDK calls by hand for routine operational tasks. It is listed as a community server in the official Model Context Protocol servers repository, and a demo video walks through the Claude Desktop setup end to end for anyone getting started with it for the first time, including how to confirm the setup by asking Claude to perform a real S3 or DynamoDB action.

Source README

AWS MCP Server

smithery badge

A Model Context Protocol server implementation for AWS operations that currently supports S3 and DynamoDB services. All operations are automatically logged and can be accessed through the audit://aws-operations resource endpoint.

AWS Server MCP server

See a demo video here.

Listed as a Community Server within the MCP servers repository.

Running locally with the Claude desktop app

Installing via Smithery

To install AWS MCP Server for Claude Desktop automatically via Smithery:

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

Manual Installation

  1. Clone this repository.
  2. Set up your AWS credentials via one of the two methods below. Note that this server requires an IAM user with RW permissions for your AWS account for S3 and DynamoDB.
  • Environment variables: AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_REGION (defaults to us-east-1)
  • Default AWS credential chain (set up via AWS CLI with aws configure)
  1. Add the following to your claude_desktop_config.json file:
  • On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
  • On Windows: %APPDATA%/Claude/claude_desktop_config.json
"mcpServers": {
  "mcp-server-aws": {
    "command": "uv",
    "args": [
      "--directory",
      "/path/to/repo/mcp-server-aws",
      "run",
      "mcp-server-aws"
    ]
  }
}
  1. Install and open the Claude desktop app.
  2. Try asking Claude to do a read/write operation of some sort to confirm the setup (e.g. create an S3 bucket and give it a random name). If there are issues, use the Debugging tools provided in the MCP documentation here.

Available Tools

S3 Operations

  • 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 Operations

Table Operations
  • 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
Item Operations
  • 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
Batch Operations
  • 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
TTL Operations
  • dynamodb_describe_ttl: Get the TTL settings for a table
  • dynamodb_update_ttl: Update the TTL settings for a table

FAQ

Common questions

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.