Hello MCP Server
A simple MCP server that provides a basic greeting tool and serves as a starter template for AWS Lambda deployment. Demonstrates how to build and deploy MCP servers with both local development and cloud deployment capabilities.
README
Hello MCP Server
Simple MCP (Model Context Protocol) server with AWS Lambda deployment.
🚀 Quick Start
Local Development
npm install
npm run dev
Connect to Claude Desktop by adding to config:
{
"mcpServers": {
"hello-mcp": {
"command": "npx",
"args": ["tsx", "/Users/mingfang/Code/hello-mcp/index.ts"]
}
}
}
Deploy to AWS Lambda
# Build and deploy
npm run deploy
# Or step by step
npm run build:lambda
sam deploy --guided
First time setup:
- Stack Name:
hello-mcp-stack - Region:
ap-southeast-2 - Bearer Token:
mcp-secret-token-12345 - Confirm all:
Y
🔑 Authentication
Bearer token: mcp-secret-token-12345
Change it:
sam deploy --parameter-overrides BearerToken="your-new-token"
🧪 Test Deployment
# Health check
curl https://gjt4ggcz76.execute-api.ap-southeast-2.amazonaws.com/health
# List available tools
curl -H "Authorization: Bearer mcp-secret-token-12345" \
https://gjt4ggcz76.execute-api.ap-southeast-2.amazonaws.com/mcp
# Call sayHello tool
curl -X POST \
-H "Authorization: Bearer mcp-secret-token-12345" \
-H "Content-Type: application/json" \
-d '{"tool": "sayHello", "params": {"name": "World"}}' \
https://gjt4ggcz76.execute-api.ap-southeast-2.amazonaws.com/mcp
🔌 Connect Claude to Lambda
Edit: ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"hello-mcp-lambda": {
"url": "https://gjt4ggcz76.execute-api.ap-southeast-2.amazonaws.com/mcp",
"transport": "http",
"headers": {
"Authorization": "Bearer mcp-secret-token-12345"
}
}
}
}
Important: Use "transport": "http" for Lambda.
🛠️ Tools
- sayHello - Greet someone by name
📋 Deployment Record
Stack Name: hello-mcp-stack
Region: ap-southeast-2
Deployed: 2025-10-17
Status: ✅ Tested and working
Outputs:
- API URL:
https://gjt4ggcz76.execute-api.ap-southeast-2.amazonaws.com/ - Lambda ARN:
arn:aws:lambda:ap-southeast-2:670326884047:function:hello-mcp-server - Authentication: Bearer token with 'http' transport
Test Results:
# ✅ Health check working
# ✅ Tool listing: ["sayHello"]
# ✅ sayHello execution: "Hello, AWS Lambda! 👋"
📁 Project Structure
hello-mcp/
├── index.ts # Local development (stdio)
├── lambda.ts # AWS Lambda handler
├── template.yaml # AWS SAM template
├── samconfig.toml # SAM configuration
├── package.json # Dependencies
└── tsconfig.json # TypeScript config
💰 Cost
Lambda free tier: 1M requests/month Expected cost: $0-5/month
📚 Learn More
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.