AWS Common MCP Servers with CDK Deployment

@vAirpower

代码仓库

基本信息

分类

云与基础设施

传输方式

stdio

作者

vAirpower

关于 AWS Common MCP Servers with CDK Deployment

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 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

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

AWS Common MCP Servers with CDK Deployment 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

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

常见问题

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).

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.

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.

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.

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.

云与基础设施分类下的更多 MCP 服务器

SimpleBackups

SimpleBackups is automated backup management for databases, servers, cloud storage and SaaS apps. It covers Supabase, Neon, PlanetScale, PostgreSQL, MySQL, MongoDB, and apps like Notion, GitHub and Linear. This connector