MCP-Server
A minimal MCP server built with TypeScript exposing a single mocked weather tool over stdio transport.
README
MCP-Server
A minimal Model Context Protocol (MCP) server built with TypeScript. It exposes a single tool, get_weather, over a stdio transport so that MCP-compatible clients (Claude Desktop, Claude Code, the MCP Inspector, etc.) can call it.
Features
- Built on
@modelcontextprotocol/sdk - Input validation via
zod - Communicates over stdio (JSON-RPC)
- One example tool:
get_weather
Prerequisites
- Node.js (v18+ recommended)
- Yarn (v1 classic or Berry)
Installation
yarn install
Build
Compiles the TypeScript source in src/ to JavaScript in build/:
yarn build
This runs tsc and marks build/index.js as executable.
Running
Start the server directly (for a quick smoke test — it will sit silently listening on stdio, which is expected):
yarn start
Start with the MCP Inspector (recommended for interactive testing/debugging):
yarn start:local
This launches a local web UI (usually at http://localhost:6274) where you can view the registered tools, call them with test inputs, and inspect the raw JSON-RPC traffic.
If running the Inspector through a Yarn script causes connection issues, run it directly instead:
npx @modelcontextprotocol/inspector node build/index.js
Available Tools
get_weather
Returns a (currently mocked) weather reading for a given city.
Input:
| Parameter | Type | Description |
|---|---|---|
city |
string | Name of the city |
Example output:
The weather in Chandigarh is 24°C and sunny.
Note: this is a stub implementation returning a random temperature. Replace the logic inside
registerTool("get_weather", ...)insrc/index.tswith a real weather API call as needed.
Connecting to an MCP Client
To use this server with Claude Desktop or another MCP client, add it to the client's config (e.g. claude_desktop_config.json):
{
"mcpServers": {
"MCP-Server": {
"command": "node",
"args": ["/absolute/path/to/MCP-Server/build/index.js"]
}
}
}
Restart the client afterward — the get_weather tool should appear as available.
Project Structure
.
├── src/
│ └── index.ts # Server entry point + tool definitions
├── build/ # Compiled output (generated by `yarn build`)
├── package.json
├── tsconfig.json
└── README.md
Extending
To add more tools, call server.registerTool(...) again inside src/index.ts with a new name, schema, and handler. For larger projects, consider splitting each tool into its own file under src/tools/ and importing them into index.ts.
License
MIT
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。