AWS MCP Server

$pip install aws-mcp-server
README.md

Interact with core AWS services like S3, EC2, RDS, and CloudWatch through Claude.

AWS MCP Server

A Model Context Protocol (MCP) server that provides tools to interact with AWS services through Claude Desktop.

Features

  • S3: List buckets, list objects
  • EC2: Describe instances, security groups, VPCs
  • RDS: Describe database instances
  • Cost Explorer: Get cost and usage reports
  • CloudWatch: Retrieve metric statistics
  • Generic AWS SDK: Access any AWS operation via aws_sdk_wrapper
  • Vector Store: Optional document ingestion and search capabilities

Quick Start

Prerequisites

  • Python 3.12+
  • AWS credentials configured (~/.aws/credentials)
  • Claude Desktop installed

Installation

  1. Install the package:

    pip install aws-mcp-server
    
  2. Configure Claude Desktop: Add to your claude_desktop_config.json:

    {
        "mcpServers": {
            "aws-mcp-server": {
                "command": "aws-mcp-server"
            }
        }
    }
    
  3. Configure AWS credentials:

    aws configure
    # OR manually edit ~/.aws/credentials:
    
    [default]
    aws_access_key_id = YOUR_ACCESS_KEY
    aws_secret_access_key = YOUR_SECRET_KEY
    region = us-east-1
    

Development

Local Development Setup

# Clone and install
git clone <repository-url>
cd aws-mcp-server
uv sync

# Run locally
uvx .

Configuration Options

Set environment variables for customization:

export AWS_MCP_PORT=8888
export AWS_MCP_DEBUG=true
export ENABLE_VECTOR_STORE=true

Documentation

License

MIT License - see LICENSE file for details.

Tools (5)

aws_sdk_wrapperAccess any AWS operation via a generic SDK wrapper.
list_s3_bucketsList all S3 buckets in the account.
describe_ec2_instancesRetrieve details about EC2 instances, security groups, and VPCs.
get_cost_and_usageGet cost and usage reports from AWS Cost Explorer.
get_metric_statisticsRetrieve CloudWatch metric statistics for monitoring.

Environment Variables

AWS_MCP_PORTPort for the MCP server to run on
AWS_MCP_DEBUGEnable debug logging
ENABLE_VECTOR_STOREEnable optional document ingestion and search capabilities

Configuration

claude_desktop_config.json
{"mcpServers": {"aws-mcp-server": {"command": "aws-mcp-server"}}}

Try it

List all my S3 buckets and show the objects in the most recent one.
Describe my running EC2 instances and their associated security groups.
Show me my AWS cost and usage report for the last 30 days.
Get the CPU utilization metrics from CloudWatch for my RDS instances.
Use the AWS SDK wrapper to check the status of my Lambda functions.

Frequently Asked Questions

What are the key features of AWS MCP Server?

Direct interaction with S3, EC2, RDS, and CloudWatch services.. Generic AWS SDK wrapper for executing any AWS operation.. Cost monitoring via AWS Cost Explorer integration.. Optional vector store for document ingestion and semantic search.. Support for standard AWS credential configuration files..

What can I use AWS MCP Server for?

Cloud infrastructure auditing and inventory management via natural language.. Quickly checking system health and CloudWatch metrics during incidents.. Monitoring AWS spend and generating usage reports for stakeholders.. Automating document search across AWS-hosted knowledge bases using the vector store.. Rapid prototyping of AWS management scripts through Claude's interface..

How do I install AWS MCP Server?

Install AWS MCP Server by running: pip install aws-mcp-server

What MCP clients work with AWS MCP Server?

AWS MCP Server works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Use AWS MCP Server with Conare

Manage MCP servers visually, upload persistent context, and never start from zero with Claude Code & Codex.

Try Free