AWS MCP Servers
@awslabs
关于 AWS MCP Servers
Open source MCP Servers for AWS
基本信息
配置
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"awslabs.bedrock-kb-retrieval-mcp-server": {
"command": "uvx",
"args": [
"awslabs.bedrock-kb-retrieval-mcp-server@latest"
],
"env": {
"AWS_PROFILE": "your-profile-name",
"AWS_REGION": "us-east-1",
"FASTMCP_LOG_LEVEL": "ERROR"
}
}
}
}工具
未检测到工具
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 MCP Servers?
AWS MCP Servers is a suite of open source MCP (Model Context Protocol) servers that give AI applications access to AWS documentation, contextual guidance, and best practices. It is designed for developers using AI‑powered IDEs, chatbots, and custom workflows to build cloud‑native applications on AWS.
How to use AWS MCP Servers?
Install and configure a server for your MCP client (Kiro, Cline, Cursor, Windsurf, VS Code, or Claude Desktop) by adding its command to the client’s mcp.json configuration file. For example, the AWS Documentation server can be added with uvx mcp-server-aws-documentation. One‑click install buttons are available for Cursor and VS Code. The servers communicate over stdio only.
Key features of AWS MCP Servers
- Provides real‑time access to official AWS documentation
- Supports infrastructure & deployment workflows (CDK, Terraform, containers)
- Includes tools for AI/ML, data analytics, and databases
- Offers specialized servers for cost, operations, and healthcare
- Enables automated code generation and infrastructure management
- Integrates with popular MCP clients (IDE, chatbot, agent)
Use cases of AWS MCP Servers
- Vibe coding and development: accelerate cloud‑native application creation
- Conversational assistants: provide up‑to‑date AWS knowledge and guidance
- Autonomous background agents: automate data operations, ETL, and monitoring
- Infrastructure as code: generate CDK or Terraform templates from natural language
- Cost & operations: query AWS billing data and resource health
FAQ from AWS MCP Servers
What transport mechanisms do AWS MCP Servers support?
The servers support stdio only. Server Sent Events (SSE) support was removed on May 26, 2025. Support for Streamable HTTP is in active development.
How do I choose between a local and a remote MCP server?
Local servers run on your machine for low‑latency, offline‑capable access. The managed AWS MCP Server (preview) is remote, hosted by AWS, and provides secure, auditable interactions with IAM permissions and full CloudTrail logging.
Which MCP clients are compatible with AWS MCP Servers?
Common clients include Kiro, Cline, Cursor, Windsurf, VS Code, and Claude Desktop. Each client has a specific mcp.json configuration location documented in the README.
What happened to Server Sent Events (SSE) in AWS MCP Servers?
SSE support was removed on May 26, 2025 to align with the MCP specification. Previous major versions remain available for applications that still require SSE until migration to
云与基础设施 分类下的更多 MCP 服务器
MCP Gateway
mcp-ecosystem🧩 MCP Gateway - A lightweight gateway service that instantly transforms existing MCP Servers and APIs into MCP servers with zero code changes. Features Docker deployment and management UI, requiring no infrastructure modifications.
GCP MCP
eniayomiA Model Context Protocol (MCP) server that enables AI assistants like Claude to interact with your Google Cloud Platform environment. This allows for natural language querying and management of your GCP resources during conversations.
Supabase MCP Server
coleam00Supabase MCP server created in Python.
Supabase MCP Server
supabase-communityConnect Supabase to your AI assistants
🐳 docker-mcp
QuantGeekDevA docker MCP Server (modelcontextprotocol)
评论