MCP LocalStack Server
Provides conversational access to LocalStack AWS services (S3, DynamoDB, Lambda, SQS) through natural language, enabling local cloud infrastructure management without real AWS costs.
README
MCP LocalStack Server
A Model Context Protocol (MCP) server that provides conversational access to LocalStack AWS services. Build, test, and debug cloud infrastructure through natural language without touching real AWS resources.
Features
- S3 Operations: Create buckets, upload/download objects, list contents
- DynamoDB: Create tables, put/get/scan items, manage data
- Lambda: Create functions, invoke them, retrieve logs
- SQS: Create queues, send/receive messages, manage queue attributes
- Zero AWS Costs: All operations run locally through LocalStack
- Natural Language Interface: Ask Claude to manage your infrastructure conversationally
Prerequisites
- Node.js >= 18.0.0
- LocalStack running locally
- Claude Desktop or any MCP-compatible client
Installation
1. Install LocalStack
# Using Docker (recommended)
docker run -d --name localstack -p 4566:4566 localstack/localstack
# Or install via pip
pip install localstack
localstack start
2. Install MCP LocalStack Server
git clone <your-repo-url>
cd mcp-localstack-server
npm install
npm run build
3. Configure Claude Desktop
Add to your Claude Desktop config file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"localstack": {
"command": "node",
"args": ["/absolute/path/to/mcp-localstack-server/dist/index.js"],
"env": {
"LOCALSTACK_ENDPOINT": "http://localhost:4566",
"AWS_REGION": "us-east-1"
}
}
}
}
Usage Examples
Once configured, you can interact with LocalStack through natural language in Claude:
S3 Operations
You: Create an S3 bucket called my-test-bucket
You: Upload a file to my-test-bucket with key data.json containing {"test": "value"}
You: List all objects in my-test-bucket
You: Get the contents of data.json from my-test-bucket
DynamoDB Operations
You: Create a DynamoDB table called Users with id as the hash key
You: Put an item in Users table: {"id": "user123", "name": "John", "email": "john@example.com"}
You: Get item from Users table with id user123
You: Scan the entire Users table
Lambda Operations
You: Create a Lambda function called hello-world using Python 3.9
You: Invoke the hello-world function with payload {"name": "Alice"}
You: Get the logs from hello-world function
SQS Operations
You: Create an SQS queue called my-queue
You: Send a message to my-queue with body "Hello from SQS"
You: Receive messages from my-queue
You: Get the attributes of my-queue
Available Tools
S3
s3_create_bucket- Create a new buckets3_list_buckets- List all bucketss3_upload_object- Upload an objects3_list_objects- List objects in a buckets3_get_object- Get object contentss3_delete_object- Delete an object
DynamoDB
dynamodb_create_table- Create a tabledynamodb_list_tables- List all tablesdynamodb_put_item- Insert an itemdynamodb_get_item- Retrieve an itemdynamodb_scan- Scan tabledynamodb_delete_item- Delete an itemdynamodb_delete_table- Delete a table
Lambda
lambda_create_function- Create a functionlambda_invoke- Invoke a functionlambda_list_functions- List all functionslambda_get_function- Get function detailslambda_delete_function- Delete a functionlambda_get_logs- Retrieve function logs
SQS
sqs_create_queue- Create a queuesqs_list_queues- List all queuessqs_send_message- Send a messagesqs_receive_messages- Receive messagessqs_delete_message- Delete a messagesqs_get_queue_url- Get queue URLsqs_delete_queue- Delete a queuesqs_get_queue_attributes- Get queue attributes
Environment Variables
LOCALSTACK_ENDPOINT- LocalStack endpoint (default:http://localhost:4566)AWS_REGION- AWS region (default:us-east-1)AWS_ACCESS_KEY_ID- Access key (default:test)AWS_SECRET_ACCESS_KEY- Secret key (default:test)
Development
# Install dependencies
npm install
# Build
npm run build
# Watch mode
npm run watch
Troubleshooting
LocalStack not responding
Ensure LocalStack is running:
docker ps | grep localstack
If not running, start it:
docker start localstack
Connection refused errors
Verify LocalStack endpoint:
curl http://localhost:4566/_localstack/health
Tools not appearing in Claude
- Restart Claude Desktop completely
- Check config file path is correct
- Verify absolute path to
dist/index.js - Check Claude Desktop logs for errors
Contributing
Contributions welcome! This project fills a gap in the MCP ecosystem and benefits from community input.
- Fork the repository
- Create a feature branch
- Make your changes
- Submit a pull request
License
MIT License - see LICENSE file for details
Why This Matters
LocalStack is a powerful tool for AWS development, but it requires knowledge of AWS CLIs, SDKs, and APIs. This MCP server makes cloud development accessible through conversation—ask Claude to manage your infrastructure instead of writing boto3 scripts or memorizing AWS CLI commands.
Perfect for:
- Learning AWS services without cost
- Testing infrastructure changes safely
- Rapid prototyping of cloud architectures
- Teaching cloud concepts interactively
- CI/CD pipeline development
Acknowledgments
Built on:
- Model Context Protocol by Anthropic
- LocalStack for local AWS simulation
- AWS SDK for JavaScript v3
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。