mcp-registry/awslabs/mcp

    ==================
      
       /// MCP ///
      /// AWS ///
        
    ==================
        
    [server:online]
    [protocol:ready]

awslabs/mcp

by awslabs

Suite of AWS-focused Model Context Protocol (MCP) servers – lightweight Python services that expose AWS tooling, documentation, pricing, IaC and other capabilities to MCP-compatible AI clients (Amazon Q, Cline, Cursor, Windsurf, etc.).

4.7k
585
Open Source
GitHubWebsiteDocumentation

Installation

1. Prerequisites
• Python ≥3.9
• AWS account with credentials configured in ~/.aws/credentials or via environment variables (AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_DEFAULT_REGION)
• (Optional) Docker if you prefer container deployment
2. Clone the repository
git clone https://github.com/awslabs/mcp.git
cd mcp
3. Create virtual environment & install dependencies
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install --upgrade pip
pip install -r requirements.txt
(If a `requirements-dev.txt` file exists, install it the same way for local testing.)
4. Build & run the MCP server locally
# Update the config file (see ./config/example-config.yaml) with your AWS settings
cp config/example-config.yaml config/config.yaml
vi config/config.yaml # or your preferred editor
# Start the server
python -m mcp.server --config ./config/config.yaml
5. Using Docker (alternative)
docker build -t aws-mcp:latest .
docker run -p 8080:8080 -e AWS_ACCESS_KEY_ID -e AWS_SECRET_ACCESS_KEY aws-mcp:latest
6. Verify
Open http://localhost:8080/health or run:
curl http://localhost:8080/health
7. Install CLI / client library (optional)
pip install aws-mcp-client # if published to PyPI
8. Deployment to AWS (optional sketch)
• Review the CDK/Terraform templates in `deploy/`
• Configure parameters (VPC, sub-nets, domain, certificate)
• Deploy: `cd deploy/cdk && cdk deploy` or follow README in the deploy folder.

Documentation

# Transform Augment Code into Your AWS Cloud Development Powerhouse

The AWS MCP Servers suite from AWS Labs is a game-changing addition to your Augment Code setup. This comprehensive collection of 40+ specialized MCP servers transforms Augment from a general coding assistant into an **AWS-native development powerhouse** that understands your cloud infrastructure, manages your resources, and follows AWS best practices automatically.

## Turn Augment Into Your AWS Expert

Instead of switching between the AWS Console, documentation, and your IDE, configure these MCP servers with Augment Code to create a unified development experience. Augment can now **directly interact with your AWS infrastructure** - deploying CDK stacks, querying DynamoDB tables, analyzing CloudWatch logs, estimating costs, and retrieving the latest AWS documentation, all through natural language conversations.

**Core servers to start with:**
- **AWS API MCP Server** - Gives Augment complete AWS API access with security controls
- **AWS Documentation MCP Server** - Provides real-time access to latest AWS docs and API references  
- **AWS CDK MCP Server** - Enables secure Infrastructure-as-Code development with compliance checking
- **AWS Pricing MCP Server** - Allows cost estimation and budget analysis before deployment

## Supercharge Your Cloud Development Workflow

With these MCP servers configured in Augment Code, you can now ask questions like:

**"Using the DynamoDB MCP server, create a user table with GSI for email lookups and show me the CDK code"** - Augment designs the table schema, creates the CDK construct, and can even deploy it directly.

**"Check my Lambda function logs for errors in the last hour and help me debug the issue"** - Augment queries CloudWatch Logs, analyzes the errors, and suggests fixes with context from your codebase.

**"What would this EKS cluster cost per month and how can I optimize it?"** - Augment calculates pricing estimates and recommends cost optimization strategies using multiple MCP servers.

The real power emerges when Augment orchestrates multiple AWS services together - analyzing your infrastructure with the CloudWatch MCP server, suggesting optimizations using the Cost Explorer MCP server, and implementing changes via the CDK MCP server, all in a single conversation.

## Setup in Minutes, Productivity Gains for Months

Adding these servers to your Augment Code configuration is straightforward. Install via `uvx` and add them to your Augment MCP settings:

```json
{
  "mcpServers": {
    "awslabs.core-mcp-server": {
      "command": "uvx",
      "args": ["awslabs.core-mcp-server@latest"]
    },
    "awslabs.cdk-mcp-server": {
      "command": "uvx", 
      "args": ["awslabs.cdk-mcp-server@latest"]
    },
    "awslabs.dynamodb-mcp-server": {
      "command": "uvx",
      "args": ["awslabs.dynamodb-mcp-server@latest"]
    }
  }
}
```

Start with the Core MCP Server for intelligent orchestration, then add specific servers based on your AWS services. The beauty is that Augment learns to use these tools contextually - automatically choosing the right MCP server for each task while maintaining security best practices and AWS compliance standards.

This isn't just about automating AWS tasks - it's about **elevating your entire cloud development process** where Augment becomes your knowledgeable AWS architect, DevOps engineer, and cost analyst all in one.
License: Apache License 2.0
Updated 7/15/2025

Table of Contents

awslabs/mcp - MCP Server Registry - Augment Code