AWS MCP Server

What does “AWS” MCP Server do?

The AWS MCP Server is a Model Context Protocol (MCP) server implementation designed for operations on AWS resources, specifically supporting S3 and DynamoDB. It acts as a bridge that enables AI assistants to interact programmatically with AWS services, allowing tasks such as creating and managing S3 buckets, uploading files, and manipulating DynamoDB tables. By exposing these AWS operations as MCP tools, the AWS MCP Server enhances development workflows and enables AI agents to automate cloud resource management, perform database queries, handle file storage, and audit actions. All operations are automatically logged and accessible via a dedicated audit resource endpoint, ensuring traceability and security in cloud-based workflows.

List of Prompts

No prompt templates were mentioned in the available documentation.

List of Resources

• audit://aws-operations
  All AWS operations performed via the server are automatically logged and accessible through this audit resource endpoint. This provides traceability and accountability for actions taken on AWS resources.

No other resources were documented.

S3 Operations

• s3_bucket_create
  Create a new S3 bucket.
• s3_bucket_list
  List all S3 buckets in the account.
• s3_bucket_delete
  Delete an existing S3 bucket.
• s3_object_upload
  Upload an object (file) to a specified S3 bucket.
• s3_object_delete
  Delete an object from a specified S3 bucket.
• s3_object_list
  List all objects in a given S3 bucket.
• s3_object_read
  Read the content of an object stored in S3.

DynamoDB Operations

• dynamodb_table_create
  Create a new DynamoDB table.

Use Cases of this MCP Server

• Automated Cloud Storage Management
  Developers can programmatically create, list, and delete S3 buckets, automate file uploads and downloads, and manage cloud storage without manual intervention.

• Database Table Provisioning
  AI assistants can create DynamoDB tables as part of automated infrastructure setup or testing workflows, streamlining database provisioning.

• File Management Automation
  Automate uploading, reading, and deleting files in S3, enabling use cases like backup, data ingestion, and document management.

• Audit and Compliance Tracking
  All operations are logged to an audit resource, supporting compliance requirements and providing an accessible activity trail for review.

• Integration with AI-Driven Workflows
  By connecting with AI agents, complex cloud workflows (such as data processing pipelines) can be managed and triggered programmatically.

How to set it up

Windsurf

No setup instructions available for Windsurf in the documentation.

Claude

1. Prerequisites:

   • Install the Claude desktop app.
   • Ensure you have Node.js and uv installed.
   • Set up AWS credentials (via environment variables or AWS CLI).

2. Clone Repository:

   • Clone this repository to your local machine.

3. Configure AWS Credentials:

   • Environment variables:
     • AWS_ACCESS_KEY_ID
     • AWS_SECRET_ACCESS_KEY
     • AWS_REGION (defaults to us-east-1)
   • Or configure using AWS CLI (aws configure).

4. Edit Claude Config:

   • Locate your claude_desktop_config.json file:
     • MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
     • Windows: %APPDATA%/Claude/claude_desktop_config.json
   • Add the following under mcpServers:

     "mcpServers": {
       "mcp-server-aws": {
         "command": "uv",
         "args": [
           "--directory",
           "/path/to/repo/mcp-server-aws",
           "run",
           "mcp-server-aws"
         ]
       }
     }
     

5. Restart Claude:

   • Save the config and restart the Claude app.
   • Test by asking Claude to perform an S3 or DynamoDB operation.

Securing API Keys Example

"env": {
  "AWS_ACCESS_KEY_ID": "your-access-key",
  "AWS_SECRET_ACCESS_KEY": "your-secret-key",
  "AWS_REGION": "us-east-1"
}

Cursor

No setup instructions available for Cursor in the documentation.

Cline

No setup instructions available for Cline in the documentation.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "mcp-server-aws": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “mcp-server-aws” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Our opinion

The AWS MCP Server offers robust AWS integration with a clear focus on S3 and DynamoDB operations, as well as proper audit logging. However, it lacks documentation for prompt templates, resource diversity, and detailed setup instructions for platforms beyond Claude. The presence of a license, stars, and forks, plus core tool support, make it a solid community server, but limited documentation for advanced MCP features (like Sampling and Roots) holds it back from a perfect score.

MCP Score

Overall rating: 7/10
This server is practical and developer-friendly for AWS automation but would benefit from expanded documentation and richer MCP feature support.