What dependencies are required?
Node.js 22+, pnpm, an AMap Open Platform Web API key, and a DingTalk custom robot webhook token.
@guog
基本信息
示例,用极简代码,演示如何构建MCP Server。
工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
Simple MCP Server is a minimal example project that demonstrates how to build an MCP server. It integrates weather queries via the AMap (Gaode) Open Platform API and sends group messages via DingTalk bots. It is intended for developers learning to build MCP servers or integrating AI chat clients with external services.
Clone the repository, install dependencies with pnpm i, and build with pnpm build. In an MCP client such as Cherry Studio, add an STDIO MCP server using node as the command and the path to build/index.js as the argument. Set the environment variables GAODE_API_KEY (32‑character AMap API key) and DINGTALK_ACCESS_TOKEN (64‑character DingTalk webhook token). After configuration, open a new conversation, enable the MCP server, and use a large model that supports function calling to trigger the tools.
Node.js 22+, pnpm, an AMap Open Platform Web API key, and a DingTalk custom robot webhook token.
Any AI chat client that supports the MCP protocol, such as Cline, Continue, Claude Desktop, and Cherry Studio.
Choose a model with function‑calling capability (marked with a 🔧 icon in Cherry Studio), for example Qwen2.5‑7B‑Instruct from SiliconFlow.
Weather data is fetched in real time from the AMap (Gaode) Open Platform weather query API.
It uses STDIO transport between the MCP client and the server. Authentication is handled via environment variables for the API keys.

Health by Dr Brad works out a health plan from your own results: which screening is due at your age, and evidence-based suggestions, each with the reason and the published guideline or study behind it. Your record is one

Model Context Protocol Servers
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
Hindsight: Agent Memory That Learns
🚀 The fast, Pythonic way to build MCP servers and clients.
评论