개요

MCP 프록시 for AWS 패키지는 AI 애플리케이션을 AWS의 MCP 서버에 연결하는 두 가지 방법을 제공합니다:

1. 프록시로 사용 - MCP 클라이언트(Claude Desktop, Kiro CLI 같은 AI 어시스턴트)와 AWS의 MCP 서버 간의 가벼운 클라이언트 측 브리지 역할을 합니다. (MCP 프록시 참조)
2. 라이브러리로 사용 - 인기 있는 AI 에이전트 프레임워크(LangChain, LlamaIndex, Strands Agents 등)를 AWS의 MCP 서버에 프로그래밍적으로 연결합니다. (프로그램 접근 참조)

이 소포는 언제 필요해?

• AWS IAM 인증(SigV4)을 사용하는 AWS의 **MCP 서버(예: Amazon Bedrock AgentCore 사용)에 연결하고 싶어 합니다
• AWS IAM 인증을 네이티브로 지원하지 않는 MCP 클라이언트(예: Claude Desktop, Kiro CLI)를 사용하고 계신다
• LangChain, Strands Agents, LlamaIndex 등과 같은 인기 프레임워크를 사용해 AWS 내 MCP 서버에 연결해야 하는 AI 에이전트를 구축하고 있습니다
• 직접 맞춤형 SigV4 요청 서명 논리를 만드는 것을 피하고 싶습니다

이 패키지가 어떻게 도움이 되는지에 대한 설명

문제점: 공식 MCP 사양은 OAuth 기반 인증을 지원하지만, AWS의 MCP 서버는 AWS IAM 인증(SigV4)도 사용할 수 있습니다.

MCP Proxy for AWS

Overview

The MCP Proxy for AWS package provides two ways to connect AI applications to MCP servers on AWS:

1. Using it as a proxy - It becomes a lightweight, client-side bridge between MCP clients (AI assistants like Claude Desktop, Kiro CLI) and MCP servers on AWS. (See MCP Proxy)
2. Using it as a library - Programmatically connect popular AI agent frameworks (LangChain, LlamaIndex, Strands Agents, etc.) to MCP servers on AWS. (See Programmatic Access)

When Do You Need This Package?

• You want to connect to MCP servers on AWS (e.g., using Amazon Bedrock AgentCore) that use AWS IAM authentication (SigV4) instead of OAuth
• You’re using MCP clients (like Claude Desktop, Kiro CLI) that don’t natively support AWS IAM authentication
• You’re building AI agents with popular frameworks like LangChain, Strands Agents, LlamaIndex, etc., that need to connect to MCP servers on AWS
• You want to avoid building custom SigV4 request signing logic yourself

How This Package Helps

The Problem: The official MCP specification supports OAuth-based authentication, but MCP servers on AWS can also use AWS IAM authentication (SigV4). Standard MCP clients don’t know how to sign requests with AWS credentials.

The Solution: This package bridges that gap by:

• Handling SigV4 authentication automatically - Uses your local AWS credentials (from AWS CLI, environment variables, or IAM roles) to sign all MCP requests using SigV4
• Providing seamless integration - Works with existing MCP clients and frameworks
• Eliminating custom code - No need to build your own MCP client with SigV4 signing logic

Which Feature Should I Use?

Use as a proxy if you want to:

• Connect MCP clients like Claude Desktop or Kiro CLI to MCP servers on AWS with IAM credentials
• Add MCP servers on AWS to your AI assistant’s configuration
• Use a command-line tool that runs as a bridge between your MCP client and AWS

→ Install mcp-proxy-for-aws-cli, the version-pinned CLI distribution: it freezes the entire dependency tree to tested versions. See MCP Proxy.

Use as a library if you want to:

• Build AI agents programmatically using popular frameworks like LangChain, Strands Agents, or LlamaIndex
• Integrate AWS IAM-secured MCP servers directly into your Python applications
• Have fine-grained control over the MCP session lifecycle in your code

→ Install mcp-proxy-for-aws, the library distribution: it keeps loose, co-resolvable dependency ranges so it resolves alongside your own dependencies. See Programmatic Access.

Prerequisites

• Install Python 3.10+
• Install the uv package manager