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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.