Simple MCP Server
A TypeScript starter template for building MCP servers with example tools (echo, math operations, time, flight status) and resources (server info, greetings). Provides a modular architecture for easily extending with custom tools and resources.
README
Simple MCP Server
A simple Model Context Protocol (MCP) server implementation using TypeScript and the official MCP SDK.
Features
This MCP server provides:
Tools
- echo: Echoes back the input text
- add_numbers: Adds two numbers together
- get_current_time: Returns the current date and time
- get_flight_status: Get real-time flight status using flight number (supports both mock and real API data)
Resources
- info://server: Server information and capabilities
- greeting://hello: A simple greeting message
Installation
- Install dependencies:
npm install
- Build the project:
npm run build
Usage
Development Mode
Run the server in development mode with hot reloading:
npm run dev
Production Mode
Build and run the compiled server:
npm run build
npm start
Watch Mode
Build and watch for changes:
npm run watch
MCP Client Integration
To use this server with an MCP client, you'll need to configure the client to connect to this server. The server uses stdio transport, so it can be launched as a subprocess.
Example configuration for MCP clients:
{
"mcpServers": {
"simple-server": {
"command": "node",
"args": ["path/to/dist/index.js"]
}
}
}
Project Structure
├── examples/ # Example implementations
│ ├── resources/
│ │ └── example-resource.ts # Example resource implementations
│ └── tools/
│ └── example-tool.ts # Example tool implementations
├── src/ # Source code
│ ├── handlers/
│ │ └── index.ts # MCP request handlers
│ ├── resources/
│ │ ├── index.ts # Resource implementations
│ │ └── registry.ts # Resource registry
│ ├── tools/
│ │ ├── index.ts # Tool implementations
│ │ └── registry.ts # Tool registry
│ ├── types/
│ │ └── index.ts # TypeScript type definitions
│ ├── utils/
│ │ └── config.ts # Configuration and utilities
│ ├── index.ts # Main entry point
│ └── server.ts # Core server implementation
├── dist/ # Compiled JavaScript (generated)
├── package.json # Node.js dependencies and scripts
├── tsconfig.json # TypeScript configuration
├── test.js # Basic test script
├── test-comprehensive.js # Comprehensive test script
└── README.md # This file
Modular Architecture
The server is built with a modular architecture that makes it easy to extend:
- Tools: Each tool is a separate class implementing the
ToolHandlerinterface - Resources: Each resource is a separate class implementing the
ResourceHandlerinterface - Registries: Central registries manage all tools and resources
- Handlers: Request handlers manage MCP protocol communication
- Types: Shared TypeScript interfaces for type safety
Development
Adding New Tools
- Create a new tool class implementing
ToolHandlerinsrc/tools/ - Add the tool to the
ToolRegistryinsrc/tools/registry.ts - See
examples/tools/example-tool.tsfor a complete example
Adding New Resources
- Create a new resource class implementing
ResourceHandlerinsrc/resources/ - Add the resource to the
ResourceRegistryinsrc/resources/registry.ts - See
examples/resources/example-resource.tsfor complete examples
Flight Status Tool
The flight status tool provides real-time flight information:
Features:
- Real-time flight status (scheduled, active, landed, cancelled, delayed)
- Departure and arrival airport information
- Airline details
- Scheduled times
- International flight support
Usage:
# Test the flight status tool
node test-flight-status.js
API Integration: By default, the tool uses mock data. To get real flight data:
- Sign up for a free API key at AviationStack
- Set the environment variable:
AVIATIONSTACK_API_KEY=your_api_key - Rebuild and restart the server
Testing
Run the test scripts to verify functionality:
# Basic test
node test.js
# Comprehensive test with all features
node test-comprehensive.js
# Test flight status tool specifically
node test-flight-status.js
Git Configuration
The project includes a comprehensive .gitignore file that excludes:
- Environment files (
.env*) containing API keys - Compiled output (
dist/) - Dependencies (
node_modules/) - IDE/editor files
- OS-specific files
- Logs and temporary files
Important Security Note: API keys and secrets are automatically excluded from git tracking.
See GITIGNORE_INFO.md for detailed information about ignored files.
MCP Protocol
This server implements the Model Context Protocol (MCP) which allows AI assistants to securely access external tools and data sources. The server communicates via JSON-RPC over stdio.
For more information about MCP, visit: https://modelcontextprotocol.io/
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.
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.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.
E2B
Using MCP to run code via e2b.