MCP Template
A production-ready Model Context Protocol server template in TypeScript that enables building MCP servers with dynamic tool registration, dual transport (stdio + HTTP), and pluggable authentication.
README
MCP Template
Production-ready Model Context Protocol server template in TypeScript — SOLID architecture, dynamic tool registration, dual transport (stdio + HTTP), and pluggable authentication.
Clone it, drop a file in src/tools/, and you have a new tool. No registry to edit, no boilerplate to wire.
Highlights
- 🔌 Drop-in tools — create
src/tools/<name>.tool.tsand it's auto-discovered and registered at startup. - 🧱 SOLID by design — clear seams between config, transport, registry, auth, and tools; dependencies injected, never reached for globally.
- 🚦 Two transports —
stdiofor local clients (Claude Desktop, Claude Code) and Streamable HTTP for remote deployments, from the same code. - 🔐 Auth in both directions — protect the server with an API key and consume external APIs with a key, both toggled by env.
- ✅ Quality baked in — strict TypeScript, Zod validation, structured logging (pino), Vitest, ESLint + Prettier, GitHub Actions, Docker.
Quick start
npm install
cp .env.example .env
npm run dev # stdio transport, hot reload
# or
TRANSPORT=http npm run dev
Build and run for production:
npm run build
npm start
Creating a tool
This is the whole workflow. Create a file ending in .tool.ts under src/tools/:
// src/tools/greet.tool.ts
import { z } from "zod";
import { defineTool } from "../core/tool.js";
export default defineTool({
name: "greet",
description: "Greets a person by name.",
inputSchema: {
name: z.string().min(1).describe("Who to greet"),
},
handler: ({ name }, { logger }) => {
logger.debug({ name }, "greeting");
return { content: [{ type: "text", text: `Hello, ${name}!` }] };
},
});
Restart the server — greet is live. The args are fully typed from inputSchema, and the second argument is the injected ToolContext (config, logger, httpClient).
Need an external API? Use the injected client instead of fetch:
const data = await httpClient.get(`/resources/${id}`);
The bundled get-current-weather.tool.ts and get-forecast.tool.ts are working references: they consult the free Open-Meteo API (no key needed) through the injected client and a dedicated WeatherService.
Configuration
All config is validated at startup in src/config/env.ts. See .env.example for every supported variable and its defaults.
Authentication
Protect the server (inbound). Set REQUIRE_AUTH=true and MCP_API_KEY=.... HTTP clients then authenticate with Authorization: Bearer <key> or x-api-key: <key>. The check is a constant-time comparison and lives behind the AuthStrategy interface — add JWT/OAuth by writing a new strategy, no transport changes.
Consume an external API (outbound). Set EXTERNAL_API_BASE_URL / EXTERNAL_API_KEY. The shared HttpClient injects the key, applies timeouts and retries, and is handed to every tool via the context.
Using with Claude Desktop
Add to claude_desktop_config.json (stdio):
{
"mcpServers": {
"mcp-template": {
"command": "node",
"args": ["/absolute/path/to/mcp-template/dist/index.js"]
}
}
}
Architecture
src/
├── index.ts Composition root: load config → pick transport
├── server.ts Builds the McpServer and runs the registry
├── config/env.ts Zod-validated environment (single source of truth)
├── core/
│ ├── tool.ts ToolDefinition contract + defineTool() helper
│ ├── tool-registry.ts Dynamic discovery & registration of *.tool.ts
│ ├── tool-context.ts Dependency-injection container for handlers
│ └── logger.ts Structured logging (to stderr, stdio-safe)
├── transports/ stdio + Streamable HTTP (with auth middleware)
├── auth/ AuthStrategy interface + API-key implementation
├── clients/ Shared HTTP client for outbound API calls
├── services/ Domain logic (e.g. WeatherService) used by tools
├── tools/ 👈 your tools — one file each, auto-registered
└── utils/errors.ts Typed errors
How SOLID shows up here:
- Single responsibility — one tool per file; registry, transport, config, and auth are each isolated.
- Open/closed — add a tool or an auth strategy by adding a file; nothing existing changes.
- Liskov — every tool is interchangeable behind
ToolDefinition. - Interface segregation — small, focused contracts (
ToolDefinition,AuthStrategy). - Dependency inversion — handlers depend on the injected
ToolContext, never on globals.
Scripts
| Script | Purpose |
|---|---|
npm run dev |
Run with hot reload (tsx) |
npm run build |
Compile to dist/ |
npm start |
Run the compiled server |
npm run typecheck |
Type-check without emitting |
npm run lint |
ESLint |
npm run format |
Prettier (write) |
npm test |
Run the test suite (Vitest) |
Docker
docker build -t mcp-template .
docker run -p 3000:3000 -e REQUIRE_AUTH=true -e MCP_API_KEY=secret mcp-template
License
MIT © Vitor Kaez
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。