MCP Server in Node.js

@lucianoayres

Basic information

About MCP Server in Node.js

MCP Server implemented in JavaScript using Node.js that demonstrates how to build an MCP server with a custom prompt and custom tools, including one that loads an environment variable from a configuration file, to integrate seamlessly with AI-assisted environments like Cursor IDE

#ai #cursor #mcp-server

MCP Server in Node.js config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-server-node": {
      "command": "npx",
      "args": [
        "@modelcontextprotocol/inspector",
        "node",
        "./mcp-server.js"
      ]
    }
  }
}

MCP Server in Node.js tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is MCP Server in Node.js?

MCP Server in Node.js is a demonstration project that implements a Model Context Protocol (MCP) server using JavaScript and Node.js. It exposes two tools—add and getApiKey—plus a predefined add_numbers prompt, allowing LLM-based IDEs like Cursor AI to call these tools on demand.

How to use MCP Server in Node.js?

Clone the repository, install dependencies with npm install, then test via the MCP Inspector using npm run inspector or npx @modelcontextprotocol/inspector node ./mcp-server.js. To integrate with Cursor IDE, add the server configuration in Cursor’s Settings → Tools & Integrations using the sample JSON provided in the README.

Key features of MCP Server in Node.js

MCP Integration exposes tool functionality to LLM-based IDEs.
Addition Tool accepts two numeric parameters and returns their sum.
MCP Prompt (“add_numbers”) helps AI models infer tool usage.
Environment variable retrieval via the getApiKey tool.
Input validation uses Zod for schema checking.
Standard I/O transport via StdioServerTransport.

Use cases of MCP Server in Node.js

Testing an MCP server interactively with MCP Inspector.
Integrating custom tools into Cursor AI for code generation.
Performing arithmetic operations through natural language prompts.
Retrieving environment variables (e.g., API keys) on demand.
Learning how to structure an MCP server with prompts and tools.

Frequently asked questions

What is the MCP framework?

MCP (Model Context Protocol) is a framework that allows you to integrate custom tools into AI-assisted development environments such as Cursor AI, enabling LLMs to call these tools on demand.

What tools are defined in this server?

Two tools are defined: **add** (takes two numbers `a` and `b` and returns their sum) and **getApiKey** (retrieves the value of the `API_KEY` environment variable).

How can I test the server before integrating with an IDE?

Use the MCP Inspector by running `npm run inspector` or `npx @modelcontextprotocol/inspector node ./mcp-server.js`, then open `http://localhost:6274/` in your browser to test tools, resources, and prompts.

What are the runtime requirements?

Node.js version 20 or higher is required.

How do I integrate this server with Cursor AI?

In Cursor IDE, go to Settings → Tools & Integrations → Add Custom MCP Server and add the JSON configuration specifying `command` (`"node"` or full path), `args` (absolute path to the server file), and optional `env` (e.g., `"API_KEY"`).

Comments

More Developer Tools MCP servers

LocalCan

Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

GripForge

gripforgeai

The tools your AI needs to make your games. Turn prompts into production-ready game assets — animated characters with their weapons attached, seamless textures, terrain, VFX, HUDs — and playable game kits Unity, Godot, U

OrangePro

Aamir Siddiqui

OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.

Moxie Docs

Jackalope-Dev

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.

Casefile

azimov777

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.