AWS MCP Server
@Havoc24k
AWS MCP Server について
概要はまだありません
基本情報
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-sa-tools-mcp-server": {
"command": "uv",
"args": [
"sync"
]
}
}
}ツール
ツールは検出されませんでした
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 MCP Server?
AWS MCP Server is a Model Context Protocol (MCP) server that provides tools to interact with AWS services through Claude Desktop. It offers built-in support for S3, EC2, RDS, Cost Explorer, CloudWatch, a generic AWS SDK wrapper, and optional vector store capabilities.
How to use AWS MCP Server?
Install the package with pip install aws-mcp-server, then configure Claude Desktop by adding "aws-mcp-server": { "command": "aws-mcp-server" } to claude_desktop_config.json. AWS credentials must be configured via aws configure or by editing ~/.aws/credentials.
Key features of AWS MCP Server
- S3: List buckets and list objects
- EC2: Describe instances, security groups, VPCs
- RDS: Describe database instances
- Cost Explorer: Get cost and usage reports
- CloudWatch: Retrieve metric statistics
- Generic AWS SDK: Access any AWS operation via
aws_sdk_wrapper - Vector Store: Optional document ingestion and search capabilities
Use cases of AWS MCP Server
- Query AWS resources (S3 buckets, EC2 instances, RDS databases) using natural language in Claude Desktop
- Retrieve AWS cost and usage reports without leaving the chat interface
- Fetch CloudWatch metric statistics interactively
- Perform arbitrary AWS SDK operations through the generic wrapper
FAQ from AWS MCP Server
What dependencies does AWS MCP Server require?
Python 3.12+ and configured AWS credentials (e.g., via ~/.aws/credentials). Claude Desktop is needed to run the MCP server.
How are AWS credentials handled?
AWS credentials must be configured before use, either by running aws configure or by manually editing ~/.aws/credentials with access key, secret key, and region.
Can I access AWS services not listed in the feature list?
Yes, the aws_sdk_wrapper tool allows calling any AWS SDK operation directly.
Is the vector store enabled by default?
No, it is optional. Set the environment variable ENABLE_VECTOR_STORE=true to activate document ingestion and search.
How do I run AWS MCP Server in a development environment?
Clone the repository, run uv sync to install dependencies, then execute uvx . to start the server locally.
「クラウドとインフラ」の他のコンテンツ
tfmcp: Terraform Model Context Protocol Tool
nwiizo🌍 Terraform Model Context Protocol (MCP) Tool - An experimental CLI tool that enables AI assistants to manage and operate Terraform environments. Supports reading Terraform configurations, analyzing plans, applying configurations, and managing state with Claude Desktop integrati
MCP Server Kubernetes
Flux159MCP Server for kubernetes management commands
Run Model Context Protocol (MCP) servers with AWS Lambda
awslabsRun existing Model Context Protocol (MCP) stdio-based servers in AWS Lambda functions
Lambda MCP Server Demo (Streamable HTTP)
mikegc-awsCreates a simple MCP tool server with "streaming" HTTP.
Mcp K8s Go
strowkMCP server connecting to Kubernetes
コメント