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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.