Netmex MCP
A lightweight and extendable MCP server toolkit that allows developers to build and integrate custom tools with AI assistants through automatic tool discovery from local directories or npm packages.
README
Netmex MCP
A lightweight and extendable Model Context Protocol (MCP) server toolkit for building custom tools that integrate with AI assistants.
This package provides a ready-to-use MCP server, a clean structure for defining tools, and the option for developers to add their own tools without modifying the package.
Installation
npm install @netmex/mcp
Or with yarn:
yarn add @netmex/mcp
Usage
After installing, you can run the MCP server using:
npx netmex-mcp
Creating Custom Tools
To add your own tools, create a tool file inside a mcp-tools/ directory in your project root:
Example Tool (TypeScript)
import type { Tool } from "@netmex/mcp/types";
const GreetTool: Tool = {
name: "greet",
description: "Returns a friendly greeting",
inputSchema: {
type: "object",
properties: {
name: { type: "string", description: "Name to greet" }
},
required: ["name"]
},
handler: async ({ name }) => ({
content: [
{
type: "text",
text: `Hello, ${name}!`
}
]
})
};
export default GreetTool;
Using Tools Inside Your Project
Once placed inside mcp-tools/, tools are automatically discovered by the loader and exposed to MCP clients.
No registration needed. No editing package code. Just drop the tool file in place.
Accessing Tool Input
Each tool receives structured arguments, validated according to its inputSchema.
Recommended Directory Layout
your-project/
├── mcp-tools/
│ ├── GreetTool.ts
│ └── AnotherTool.ts
├── node_modules/
├── package.json
└── ...
NPM Plugin Tools
You can also install tools from npm. Any dependency whose name starts with:
netmex-mcp-tool-
will be auto-loaded by the server.
Example:
npm install netmex-mcp-tool-analytics
Handling Errors
If a tool throws or returns an invalid value, the server automatically returns a JSON-RPC error:
{
"error": {
"code": -32603,
"message": "Internal error",
"data": { "details": "Something went wrong" }
}
}
Use try/catch inside handlers for custom error responses.
Built-In Tools
This package includes a few tools by default:
- about
- hello
- (more coming soon)
Development
To build the MCP server locally:
npm install
npm run build
To start it directly:
npm run start
More About MCP
For more information on the Model Context Protocol, visit the official MCP documentation.
License
This project is licensed under the MIT License.
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。