AWS MCP Servers
Official AWS Labs collection of MCP servers — CDK infrastructure generation, Bedrock model access, AWS docs lookup, cost analysis, and more in a single monorepo.
Open source MCP servers for AWS
A suite of specialized MCP servers that help you get the most out of AWS, wherever you use MCP.
Table of Contents
- Open source MCP servers for AWS
- Table of Contents
- What is the Model Context Protocol (MCP) and how does it work with MCP Servers for AWS?
- Open source MCP servers for AWS Transport Mechanisms
- Why MCP Servers for AWS?
- Available MCP Servers: Quick Installation
- 🚀Getting Started with AWS
- Browse by What You're Building
- Browse by How You're Working
- MCP AWS Lambda Handler Module
- When to use Local vs Remote MCP Servers?
- Use Cases for the Servers
- Installation and Setup
- Samples
- Vibe coding
- Additional Resources
- Security
- Contributing
- Developer guide
- License
- Disclaimer
What is the Model Context Protocol (MCP) and how does it work with MCP Servers for AWS?
The Model Context Protocol (MCP) is an open protocol that enables seamless integration between LLM applications and external data sources and tools. Whether you're building an AI-powered IDE, enhancing a chat interface, or creating custom AI workflows, MCP provides a standardized way to connect LLMs with the context they need.
An MCP Server is a lightweight program that exposes specific capabilities through the standardized Model Context Protocol. Host applications (such as chatbots, IDEs, and other AI tools) have MCP clients that maintain 1:1 connections with MCP servers. Common MCP clients include agentic AI coding assistants (like Kiro, Cline, Cursor, Windsurf) as well as chatbot applications like Claude Desktop, with more clients coming soon. MCP servers can access local data sources and remote services to provide additional context that improves the generated outputs from the models.
MCP Servers for AWS use this protocol to provide AI applications access to AWS documentation, contextual guidance, and best practices. Through the standardized MCP client-server architecture, AWS capabilities become an intelligent extension of your development environment or AI application.
MCP Servers for AWS enable enhanced cloud-native development, infrastructure management, and development workflows—making AI-assisted cloud computing more accessible and efficient.
The Model Context Protocol is an open source project run by Anthropic, PBC. and open to contributions from the entire community. For more information on MCP, you can find further documentation here
Open source MCP servers for AWS Transport Mechanisms
Supported transport mechanisms
The MCP protocol currently defines two standard transport mechanisms for client-server communication:
- stdio, communication over standard in and standard out
- streamable HTTP
The MCP servers in this repository are designed to support stdio only.
You are responsible for ensuring that your use of these servers comply with the terms governing them, and any laws, rules, regulations, policies, or standards that apply to you.
Server Sent Events Support Removal
Important Notice: On May 26th, 2025, Server Sent Events (SSE) support was removed from all MCP servers in their latest major versions. This change aligns with the Model Context Protocol specification's backwards compatibility guidelines.
We are actively working towards supporting Streamable HTTP, which will provide improved transport capabilities for future versions.
For applications still requiring SSE support, please use the previous major version of the respective MCP server until you can migrate to alternative transport methods.
Why MCP Servers for AWS?
MCP servers enhance the capabilities of foundation models (FMs) in several key ways:
-
Improved Output Quality: By providing relevant information directly in the model's context, MCP servers significantly improve model responses for specialized domains like AWS services. This approach reduces hallucinations, provides more accurate technical details, enables more precise code generation, and ensures recommendations align with current AWS best practices and service capabilities.
-
Access to Latest Documentation: FMs may not have knowledge of recent releases, APIs, or SDKs. MCP servers bridge this gap by pulling in up-to-date documentation, ensuring your AI assistant always works with the latest AWS capabilities.
-
Workflow Automation: MCP servers convert common workflows into tools that foundation models can use directly. Whether it's CDK, Terraform, or other AWS-specific workflows, these tools enable AI assistants to perform complex tasks with greater accuracy and efficiency.
-
Specialized Domain Knowledge: MCP servers provide deep, contextual knowledge about AWS services that might not be fully represented in foundation models' training data, enabling more accurate and helpful responses for cloud development tasks.
Available MCP Servers: Quick Installation
Get started quickly with one-click installation buttons for popular MCP clients. Click the buttons below to install servers directly in Cursor or VS Code:
🚀 Getting Started with AWS
For AWS interactions, we recommend starting with:
| Server Name | Description | Install |
|---|---|---|
| AWS MCP Server (in preview) | Start here for secure, auditable AWS interactions! This remote, managed MCP server is hosted by AWS and combines comprehensive AWS API support with access to the latest AWS documentation, API references, What's New posts, and Getting Started information. Features pre-built Agent SOPs that follow AWS best practices, helping agents complete complex multi-step AWS tasks reliably. Built with safety and control in mind: syntactically validated API calls, IAM-based permissions with zero credential exposure, and complete CloudTrail audit logging. Access all AWS services for managing infrastructure, exploring resources, and executing AWS operations with full transparency and traceability. Read more |    |
Browse by What You're Building
📚 Real-time access to official AWS documentation
| Server Name | Description | Install |
|---|---|---|
| AWS Knowledge MCP Server | A remote, fully-managed MCP server hosted by AWS that provides access to the latest AWS docs, API references, What's New Posts, Getting Started information, Builder Center, Blog posts, Architectural references, and Well-Architected guidance. | |
| AWS Documentation MCP Server | Get latest AWS docs and API references | |
🏗️ Infrastructure & Deployment
Build, deploy, and manage cloud infrastructure with Infrastructure as Code best practices.
| Server Name | Description | Install |
|---|---|---|
| AWS IaC MCP Server | Complete Infrastructure as Code toolkit with CloudFormation documentation access, CDK best practices guidance, construct examples, security validation, and deployment troubleshooting | |
| AWS Cloud Control API MCP Server ⚠️ DEPRECATED | Direct AWS resource management with security scanning and best practices (Use AWS IaC MCP Server instead) | |
| AWS CDK MCP Server ⚠️ DEPRECATED | AWS CDK development with security compliance and best practices (Use AWS IaC MCP Server instead) | |
| AWS Terraform MCP Server ⚠️ DEPRECATED | Terraform workflows with integrated security scanning (Use HashiCorp's official Terraform MCP Server instead) | |
| AWS CloudFormation MCP Server | Direct CloudFormation resource management via Cloud Control API | |
Container Platforms
| Server Name | Description | Install |
|---|---|---|
| Amazon EKS MCP Server | Kubernetes cluster management and application deployment | |
| Amazon ECS MCP Server | Container orchestration and ECS application deployment | |
| Finch MCP Server | Local container building with ECR integration | |
Serverless & Functions
| Server Name | Description | Install |
|---|---|---|
| AWS Serverless MCP Server | Complete serverless application lifecycle with SAM CLI | |
| AWS Lambda Tool MCP Server | Execute Lambda functions as AI tools for private resource access | |
Support
| Server Name | Description | Install |
|---|---|---|
| AWS Support MCP Server | Help users create and manage AWS Support cases | |
🤖 AI & Machine Learning
Enhance AI applications with knowledge retrieval, content generation, and ML capabilities
| Server Name | Description | Install |
|---|---|---|
| Amazon Bedrock Knowledge Bases Retrieval MCP Server | Query enterprise knowledge bases with citation support | |
| Amazon Kendra Index MCP Server | Enterprise search and RAG enhancement | |
| Amazon Q Business MCP Server | AI assistant for your ingested content with anonymous access | |
| Amazon Q Index MCP Server | Data accessors to search through enterprise's Q index | |
| Nova Canvas MCP Server ⚠️ DEPRECATED | AI image generation using Amazon Nova Canvas (Use bedrock-image-mcp-server instead) | |
| AWS Bedrock Data Automation MCP Server ⚠️ DEPRECATED | Analyze documents, images, videos, and audio files (Use boto3 API or aws-api-mcp-server instead) | |
| AWS Bedrock Custom Model Import MCP Server | Manage custom models in Bedrock for on-demand inference | |
| AWS Bedrock AgentCore MCP Server | Provides comprehensive documentation access on AgentCore platform services, APIs, and best practices | |
| Amazon SageMaker AI MCP Server | SageMaker AI resource management and model development | |
📊 Data & Analytics
Work with databases, caching systems, and data processing workflows.
SQL & NoSQL Databases
| Server Name | Description | Install |
|---|---|---|
| Amazon DynamoDB MCP Server | DynamoDB expert design guidance and data modeling assistance | |
| Amazon Aurora PostgreSQL MCP Server | PostgreSQL database operations via RDS Data API | [![Insta |
More MCP Servers
Playwright MCP
Official Microsoft Playwright MCP server — give Claude full browser automation: navigate pages, click elements, fill forms, take screenshots, and scrape content.
Container Use (Dagger)
Official Dagger MCP server — give Claude isolated container environments per task. Each agent gets its own container with configurable tools, filesystem, and network access.
E2B Code Sandbox MCP
Official E2B MCP server — execute arbitrary code in secure cloud sandboxes, run scripts in isolated environments, and get output back in Claude without local execution risks.