How do I install AWS MCP Deployment MCP Server?

Follow the setup instructions on the AWS MCP Deployment GitHub repository, then add the server configuration to your AI client.

What category is AWS MCP Deployment MCP Server?

AWS MCP Deployment is categorized under Cloud Services. Browse more servers in these categories on MCPgee.

AWS MCP Deployment

Name: Guidance For Deploying Model Context Protocol Servers On Aws MCP Server
Author: aws-solutions-library-samples

v1.0.0•Cloud Services•stable

This Guidance demonstrates how to securely run Model Context Protocol (MCP) servers on the AWS Cloud using containerized architecture. It helps organizations implement industry-standard OAuth 2.0 authentication while protecting server deployments wit

guidance-for-deploying-model-context-protocol-servers-on-awsmcpai-integration

151

Stars

Downloads

Weekly

0/5

View on GitHub

What is AWS MCP Deployment?

AWS MCP Deployment is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to this guidance demonstrates how to securely run model context protocol (mcp) servers on the aws cloud using containerized architecture. it helps organizations implement industry-standard oauth 2.0 auth...

This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

This Guidance demonstrates how to securely run Model Context

Use Cases

This Guidance demonstrates how to securely run Model Context Protocol (MCP) serv

aws-solutions-library-samples

Maintainer

LicenseMIT-0

Languagetypescript

Versionv1.0.0

UpdatedMay 19, 2026

Statushealthy

Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

View Source Browse All Servers

Installation

Manual Installation

npx guidance-for-deploying-model-context-protocol-servers-on-aws

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms

ThroughputMedium

Resource Usage

Memory UsageLow

CPU UsageLow

How to Set Up and Use AWS MCP Deployment

This AWS Solutions Library guidance shows how to securely deploy Model Context Protocol servers on AWS using a containerized, cloud-native architecture. It implements the 2025 MCP specification with OAuth 2.0 Protected Resource Metadata (RFC 9728) authentication, CloudFront WAF protection, and StreamableHTTP transport. Organizations use it to run production-grade, multi-tenant MCP endpoints on ECS Fargate or AWS Lambda without managing raw infrastructure, estimated at around $194/month for moderate traffic.

Prerequisites

AWS account with permissions to deploy CDK stacks (VPC, ECS, Lambda, CloudFront, Cognito, WAF)
Node.js v14+ and AWS CDK installed locally (`npm install -g aws-cdk`)
AWS CLI configured with credentials (`aws configure`)
Docker installed and authenticated to ECR Public (`aws ecr-public get-login-password --region us-east-1`)
An MCP client such as Claude Desktop or a custom Python client

Clone the repository

Clone the AWS Solutions Library sample and navigate to the CDK deployment directory for ECS and Lambda.

git clone https://github.com/aws-solutions-library-samples/guidance-for-deploying-model-context-protocol-servers-on-aws.git
cd guidance-for-deploying-model-context-protocol-servers-on-aws/source/cdk/ecs-and-lambda

Install dependencies

Install Node.js dependencies required by the CDK application.

npm install

Authenticate Docker to ECR Public

aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws

Deploy all CDK stacks

Run `cdk deploy --all` to provision the four stacks: VPC, Security, CloudFront WAF, and MCP Server. Optionally pass certificate ARNs and a custom domain as context variables for HTTPS support.

cdk deploy --all
# Or with a custom domain and certificate:
# cdk deploy --all --context domainName=mcp.example.com --context certificateArn=arn:aws:acm:...

Create a Cognito test user

After deployment, create an Amazon Cognito user with a permanent password to test OAuth 2.0 authentication against the deployed endpoints.

aws cognito-idp admin-create-user --user-pool-id <USER_POOL_ID> --username testuser --temporary-password Temp1234!
aws cognito-idp admin-set-user-password --user-pool-id <USER_POOL_ID> --username testuser --password Perm5678! --permanent

Test with the Python client

Use the included Python test client to exercise the deployed endpoints. Set the required environment variables pointing to your CloudFront URL and Cognito credentials, then run the client.

export MCP_SERVER_URL=https://<cloudfront-endpoint>/weather-nodejs/mcp
export OAUTH_CLIENT_ID=<cognito-client-id>
export OAUTH_CLIENT_SECRET=<cognito-client-secret>
python source/tests/python-client/client.py

Update or add MCP servers

To deploy changes to an existing server or add a new one, re-run the MCP Server stack only. This avoids redeploying the VPC and security infrastructure.

cdk deploy MCP-Server

AWS MCP Deployment Examples

Client configuration

Because this guidance runs MCP servers as remote HTTP endpoints behind CloudFront, connect from Claude Desktop using the StreamableHTTP transport with your CloudFront URL.

{
  "mcpServers": {
    "aws-weather-mcp": {
      "url": "https://<cloudfront-endpoint>/weather-nodejs/mcp"
    }
  }
}

Prompts to try

Once connected through a compatible MCP client to the deployed weather server endpoint, try these prompts to verify the setup works.

- "What is the current weather forecast for Seattle, WA?"
- "Show me the weather alerts active in California right now."
- "Get the hourly forecast for New York City for the next 12 hours."

Troubleshooting AWS MCP Deployment

CDK deployment fails with 'No space left on device' or Docker image pull errors

Ensure Docker is running and you have authenticated to ECR Public with the `aws ecr-public get-login-password` command before running `cdk deploy --all`.

Python client returns 401 Unauthorized when hitting the MCP endpoint

Verify OAUTH_CLIENT_ID and OAUTH_CLIENT_SECRET match the Cognito app client values. Also confirm the Cognito user password has been set to permanent status using `admin-set-user-password --permanent`.

CloudFront returns 403 Forbidden for all requests

Check that the WAF rules are not blocking your IP. Review the WAF logs in CloudWatch and ensure your client sends the correct Origin header expected by the CloudFront distribution.

Frequently Asked Questions about AWS MCP Deployment

What is AWS MCP Deployment?

AWS MCP Deployment is a Model Context Protocol (MCP) server that this guidance demonstrates how to securely run model context protocol (mcp) servers on the aws cloud using containerized architecture. it helps organizations implement industry-standard oauth 2.0 authentication while protecting server deployments wit It connects AI assistants to external tools and data sources through a standardized interface.

How do I install AWS MCP Deployment?

Follow the installation instructions on the AWS MCP Deployment GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with AWS MCP Deployment?

AWS MCP Deployment works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is AWS MCP Deployment free to use?

Yes, AWS MCP Deployment is open source and available under the MIT-0 license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

AWS MCP Deployment Alternatives — Similar Cloud Services Servers

Looking for alternatives to AWS MCP Deployment? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.

Open WebUI

★ 138.2k

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Anything LLM

★ 60.4k

The all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.

LocalAI

★ 46.4k

LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.

Nacos

★ 33.0k

an easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.

Xiaozhi ESP32

★ 26.7k

本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.

Gateway

★ 11.8k

A blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.

Browse More Cloud Services MCP Servers

Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Cloud Services Browse All Servers

Set Up AWS MCP Deployment in Your Editor

Choose your AI client for step-by-step setup instructions.

🖥️

Claude Desktop

macOS & Windows app

⌨️

Claude Code

CLI & terminal

📝

Cursor

AI-first code editor

💻

VS Code

GitHub Copilot MCP

🏄

Windsurf

Codeium AI editor

🔌

Cline

VS Code extension

Quick Config Preview

{
  "mcpServers": {
    "guidance-for-deploying-model-context-protocol-servers-on-aws": {
      "command": "npx",
      "args": ["-y", "guidance-for-deploying-model-context-protocol-servers-on-aws"]
    }
  }
}

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use AWS MCP Deployment?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides

Explore All Servers Read Our Guides