AWS

What is mcp-server-aws?

mcp-server-aws is a Model Context Protocol (MCP) server implementation that allows users to interact with AWS resources using a Large Language Model (LLM), specifically designed to work with the Claude desktop app. It provides a set of tools to perform operations on Amazon S3 and DynamoDB services, with all operations automatically logged for auditing purposes.

How to use mcp-server-aws?

mcp-server-aws can be installed and used with the Claude desktop app. There are two primary installation methods:

• Installing via Smithery: Use the npx -y @smithery/cli install mcp-server-aws --client claude command for automatic installation.
• Manual Installation: This involves cloning the repository, setting up AWS credentials (environment variables or AWS CLI), and configuring the claude_desktop_config.json file to include the server. An IAM user with read/write permissions for S3 and DynamoDB is required.

After installation, users can interact with AWS resources by asking Claude to perform read/write operations (e.g., creating an S3 bucket).

Key Features of mcp-server-aws

• LLM-driven AWS Operations: Enables interaction with AWS services (S3 and DynamoDB) through natural language via an LLM.
• S3 Operations: Comprehensive tools for S3, including creating, listing, deleting buckets, and uploading, deleting, listing, and reading objects.
• DynamoDB Operations: Extensive tools for DynamoDB, covering table operations (create, describe, delete, update), item operations (put, get, update, delete, query, scan), batch operations (get, write, execute), and TTL operations (describe, update).
• Automatic Logging: All AWS operations performed through the server are automatically logged and accessible via the audit://aws-operations resource endpoint.
• Community Server: Listed as a Community Server within the MCP servers repository, indicating community support and recognition.
• Easy Integration: Designed for seamless integration with the Claude desktop app.

Use Cases of mcp-server-aws

• Simplified AWS Management: Users can manage S3 buckets and DynamoDB tables using natural language commands, reducing the need for direct console or CLI interaction.
• Automated Cloud Tasks: Automate routine AWS tasks through LLM prompts, such as creating storage, managing database entries, or retrieving data.
• Developer Productivity: Developers can quickly prototype and test AWS interactions without writing extensive code, leveraging the LLM for rapid development.
• Auditing and Compliance: The automatic logging of operations provides a clear audit trail for compliance and security monitoring.
• Educational Purposes: A user-friendly way to learn and experiment with AWS services for those familiar with LLMs.

FAQ from mcp-server-aws

• What AWS services are supported? Currently, S3 and DynamoDB services are supported.
• What permissions are required? An IAM user with read/write permissions for S3 and DynamoDB in your AWS account is necessary.
• How can I debug issues? The MCP documentation provides debugging tools to assist with troubleshooting.
• Is there a demo available? Yes, a demo video is available via a Loom link provided in the README.

AWS MCP Server

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.

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)

3. 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"
    ]
  }
}

4. Install and open the Claude desktop app.
5. 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