MCP Weather Demo
A demonstration server for ModelContextProtocol that provides weather tools and prompts for Claude AI, allowing LLMs to access external data without manual copying.
README
mcp
A demo of the ModelContextProtocol (MCP) using the Anthropic AI SDK.
Built following the Server Quickstart and the Client Quickstart.
Getting Started
Prerequisites
- Bun (v1.2.17)
- asdf (optional)
- asdf-bun (optional)
- Claude Desktop (required if only running the server)
Installation
If using asdf, run:
asdf install
Regardless of whether using asdf or not, install dependencies:
bun install
Server
The server allows a client to access resources, tools, and prompts.
It needs a client to interact with an LLM. Claude Desktop serves as the client if you are only running the server.
Set Up
You need to add the server to Claude Desktop by modifying the claude_desktop_config.json file in your Library/Application Support/Claude directory. If this file does not exist, you can create it.
vi ~/.config/Claude/claude_desktop_config.json
Add the following to the file:
{
"mcpServers": {
"weather": {
"command": "/ABSOLUTE/PATH/TO/bin/bun",
"args": ["/ABSOLUTE/PATH/TO/src/server/index.ts"]
}
}
}
⚠️ Bun Path
If you are using asdf, you will need to use the absolute path to the bun executable. You can find this by running asdf where bun.
If you're just using bun without asdf, you can use bun as the command.
Run
Once you've modified the claude_desktop_config.json file, restart Claude Desktop.
You should now see the weather tools and prompts in Claude Desktop!
Client
Instead of using Claude Desktop, you can also run a client to handle the interaction with the LLM.
This would suitable for building a chat interface or web application that uses Anthropic's API. With MCP, you can give the LLM access to data without having to manually copy and paste them into a prompt.
Set Up
Get an Anthropic API key from the Anthropic API Keys page.
Create a .env file in the root of the project and add the following:
ANTHROPIC_API_KEY=your_api_key_here
Run
Now you can run the client:
bun run dev
This gives you an interactive CLI where you can ask the LLM questions. Note that you have access to the tools defined in the server!
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。