広告掲載
MCP.so
ログイン

AWS Common MCP Servers with CDK Deployment

@vAirpower

リポジトリ

基本情報

カテゴリ

クラウドとインフラ

トランスポート

stdio

作者

vAirpower

AWS Common MCP Servers with CDK Deployment について

Deployable MCP Servers for common AWS services (Location, S3, Aurora PG Data API) using AWS CDK.

#aws#mcp#cdk#cloud-services

AWS Common MCP Servers with CDK Deployment の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "aws-common-mcp-servers": {
      "command": "python3",
      "args": [
        "-m",
        "venv",
        ".venv"
      ]
    }
  }
}

AWS Common MCP Servers with CDK Deployment のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is AWS Common MCP Servers with CDK Deployment?

AWS Common MCP Servers with CDK Deployment provides deployable Model Context Protocol (MCP) servers for common AWS services, along with AWS Cloud Development Kit (CDK) code (Python) to provision the necessary infrastructure for running these servers, typically on ECS Fargate. It offers reusable components that AI developers using Amazon Bedrock or LangChain can easily deploy into their AWS accounts to interact with AWS services through the standardized MCP interface.

How to use AWS Common MCP Servers with CDK Deployment?

Deploy by cloning the repository, installing CDK dependencies (pip install -r requirements.txt), bootstrapping CDK (cdk bootstrap), and running cdk deploy --all. For the Aurora PostgreSQL server, you must configure db_cluster_arn and db_secret_arn in the CDK stack file beforehand. Once deployed, the servers run as ECS Fargate tasks and can be invoked from within your AWS environment (e.g., Lambda functions, Bedrock Agents). Local testing is possible by running the server scripts directly after installing dependencies and setting required environment variables.

Key features of AWS Common MCP Servers with CDK Deployment

  • Includes MCP servers for AWS Location Service, S3, and Aurora PostgreSQL
  • Infrastructure provisioned automatically using CDK on ECS Fargate
  • Written in TypeScript (Location Service) and Python (S3, Aurora)
  • Prerequisites: AWS account, Node.js, Python 3.9+, CDK CLI, Docker
  • Aurora server requires an existing cluster with RDS Data API enabled
  • Deployment builds Docker images, pushes to ECR, and creates ECS services

Use cases of AWS Common MCP Servers with CDK Deployment

  • Enable AI agents to search places and calculate routes via AWS Location Service
  • Allow AI agents to list, get, put, and delete objects in S3 buckets
  • Let AI agents execute SQL queries on an Aurora PostgreSQL cluster via RDS Data API
  • Deploy a consistent MCP server infrastructure for multiple AWS services in one account

よくある質問

1

Which MCP servers are included?

The project includes three servers: AWS Location Service (TypeScript), Amazon S3 (Python), and Amazon Aurora PostgreSQL via RDS Data API (Python).

2

What are the prerequisites for the Aurora PostgreSQL server?

You need an existing Aurora PostgreSQL cluster with the RDS Data API enabled, and an AWS Secrets Manager secret containing the database credentials (username, password). The ARNs of both the cluster and the secret must be configured in the CDK stack file.

3

How do I deploy the servers?

Clone the repository, install CDK dependencies in a Python virtual environment, bootstrap CDK if needed, then run `cdk deploy --all` (or specific stack names). Deploy all stacks requires Docker running locally to build container images.

4

How do I access the servers after deployment?

The servers run on ECS Fargate and are not publicly exposed. Interaction happens from within your AWS environment, typically via invoking the ECS tasks from Lambda or Bedrock Agents using the AWS SDK.

5

How do I clean up the deployed resources?

Run `cdk destroy` from the `cdk_deployment` directory after activating the virtual environment. This removes all infrastructure provisioned by the CDK stacks.

コメント

「クラウドとインフラ」の他のコンテンツ

Muumuu Domain MCP Server

pepabo

The official MCP server for Muumuu Domain by GMO Pepabo, Inc — the first remote MCP server in the Japanese domain registrar industry. Search and register domains, manage owned domains and contracts, and configure DNS rec

1

Kubernetes MCP Server

manusa

Model Context Protocol (MCP) server for Kubernetes and OpenShift

1.8K

SnapDeploy MCP

AAR-Labs

Deploy and manage SnapDeploy apps (Docker containers on AWS) from Claude Code, Cursor, Codex or Gemini CLI: builds, logs, env vars, add-ons, domains.

HostTracker

HostTracker

HostTracker is a website and infrastructure monitoring service that has run external checks since 2004 for more than 500,000 websites. Its official MCP server lets an AI assistant operate a HostTracker account directly i

container-use

aluzzardi

Development environments for coding agents. Enable multiple agents to work safely and independently with your preferred stack.

3.9K
広告掲載