Express MCP Server
A modular Model Context Protocol server implementation using Express.js that provides example mathematical and echo tools with HTTP streaming support and easy extensibility for adding custom tools.
README
Express MCP Server
A clean, modular implementation of the Model Context Protocol (MCP) using Express.js and TypeScript.
Quick Start
# Install dependencies
npm install
# Development (with file watching)
npm run dev
# Production
npm run build
npm start
# Type checking
npm run type-check
Server runs on http://localhost:3001
Endpoints
- Health:
GET /mcp/health- Server health status - Info:
GET /mcp/info- Server information and capabilities - MCP Protocol:
POST/GET/DELETE /mcp- Main MCP endpoints with streaming support
Project Structure
src/
├── index.ts Entry point - starts the server
├── app.ts Express app factory
├── server/
│ └── mcp.ts Core MCP server logic
├── routes/
│ └── mcp.ts HTTP route handlers
└── tools/
└── index.ts Tool definitions
Total: 201 lines of focused, readable code
Architecture
Single Responsibility Principle
Each module has one clear purpose:
index.ts(10 lines) - Server startupapp.ts(20 lines) - Express setupserver/mcp.ts(60 lines) - MCP protocol handlingroutes/mcp.ts(69 lines) - HTTP routingtools/index.ts(42 lines) - Tool catalog
Features
✓ Official MCP SDK integration (StreamableHTTPServerTransport)
✓ HTTP streaming (chunked encoding + Server-Sent Events)
✓ Session management with automatic UUID generation
✓ Zod schema validation for tool inputs
✓ Comprehensive error handling
✓ Health check and info endpoints
✓ TypeScript strict mode
Tools
Three example tools are included:
- add(a, b) - Add two numbers
- multiply(x, y) - Multiply two numbers
- echo(message) - Echo a message
Adding a New Tool
Edit src/tools/index.ts and add to the array:
{
name: "my-tool",
description: "What this tool does",
inputSchema: {
param1: z.string().describe("Parameter description"),
param2: z.number().describe("Another parameter"),
},
handler: async (args) => {
const p1 = args.param1 as string;
const p2 = args.param2 as number;
// Tool logic here
return `Result: ${p1} ${p2}`;
},
}
Then rebuild:
npm run build
npm start
Testing
# Health check
curl http://localhost:3001/mcp/health
# Server info
curl http://localhost:3001/mcp/info
# MCP protocol request (with proper headers)
curl -X POST http://localhost:3001/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'
Development
# Watch mode (recompiles on file changes)
npm run dev
# Type checking only
npm run type-check
# Build production bundle
npm run build
Environment Variables
PORT(default: 3001) - Server port
PORT=4000 npm start
Stack
- Express.js - Web framework
- TypeScript - Type safety
- Zod - Schema validation
- MCP SDK - Protocol implementation
- Node.js 18+ - Runtime
Standards
- MCP Protocol Version: 2024-11-05
- HTTP Streaming: Chunked encoding + SSE
- Schema Validation: Zod
- Code Format: TypeScript with strict mode
- Code Style: Tabs, consistent formatting
Documentation
- ARCHITECTURE.md - Detailed architecture overview
- QUICK_START.md - 5-minute setup guide
- COMMANDS.md - Command reference
- REFACTORING_SUMMARY.md - Development history
License
MIT
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.