AWS
- typescript
27
GitHub Stars
typescript
Language
4 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
You can use this MCP server to spin up AWS infrastructure through natural language prompts. It exposes a structured way to manage services like EC2, VPC, S3, RDS, and more, enabling you to programmatically create and configure AWS resources via a conversational interface. This guide walks you through how to run and use the server locally and through Docker, and how to connect your MCP client to it.
How to use
Connect to the MCP server from your client and start issuing prompts to create and manage AWS resources. You will interact with the server through an MCP channel that streams responses as actions are performed. Begin with your usual AWS credentials, either through configured headers when using a local/dev setup or via environment variables if you deploy the server in a container. Use the available tools to create VPCs, subnets, security groups, EC2 instances, and related networking components, then extend your setup with additional services like RDS and S3 as needed.
How to install
Prerequisites: Node.js >= 18.0.0 and pnpm >= 10.0.0. For Docker deployment, ensure Docker and Docker Compose are installed. You will also need an AWS account with credentials (Access Key ID and Secret Access Key).
Step-by-step setup using the local development flow:
# 1) Install dependencies
pnpm install
# 2) Run the dev server
pnpm dev
Additional notes
Configuration relies on AWS credentials supplied via HTTP headers in development and local usage. If you deploy with Docker, credentials are still passed in the same manner. A typical workflow includes building a container image (optional) and running the server to expose endpoints for MCP clients to connect.
Environment variables commonly used with MCP connections include AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, and AWS_SESSION_TOKEN. Ensure these are available to the server in your chosen deployment method.
Available tools
rds
Manage RDS databases, including creation, listing, updating, and deletion of instances and snapshots.
s3
Operate on S3 buckets and objects, enabling creation, listing, uploading, and deletion.
ec2
Handle EC2 instances, AMIs, key pairs, and instance lifecycle actions.
vpc
Create and configure VPCs, subnets, and routing resources.
subnet
Manage subnet resources within VPCs, including CIDR allocation and associations.
internet_gateway
Create and attach Internet Gateways to VPCs for internet access.
route_table
Define and associate route tables to control traffic routing.
security_group
Set up security groups to control inbound and outbound traffic.
key_pair
Create and manage EC2 key pairs for SSH access.
instance_tag
Assign and manage tags on EC2 instances for organization and filtering.
ami
Manage AMI listings and usage for launching instances.