Test

Learning How to Build MCP Tools in cursor

javascript

0

GitHub Stars

javascript

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "shahzaibalikhawaja-model-context-protocols": {
      "command": "node",
      "args": [
        "server.js"
      ],
      "env": {
        "NODE_OPTIONS": "--max-old-space-size=2048"
      }
    }
  }
}

A simple MCP Server that demonstrates how a local tool-enabled environment can be used by an AI model to call tools, read resources, and return structured results with validation and clear errors.

How to use

You connect an MCP client to this server to run tools, access resources, and receive structured responses. Use the client to send tool calls and resource reads; the server will validate inputs, execute the requested tool, and return a well-formed response that the client can present to you.

How to install

Prerequisites: you need Node.js and npm installed on your machine.

Install dependencies.

Configuration and runtime notes

This server provides several example tools and resources to help you learn MCP usage and validation.

Tools (validated with Zod) include echo, add_numbers, get_system_info, and validate_email. Resources include sample text and JSON files to illustrate content retrieval.

Run the server in local stdio mode with one of the following commands. Use the complete command as shown to ensure proper startup.

Server startup configurations

Two explicit local runtime configurations are shown for connecting this server to a client. Each configuration runs the MCP server as a local process using Node.js.

Troubleshooting

If you encounter issues, ensure dependencies are installed, the server file is executable, and that you restart the client after any configuration change. Check for clear error messages that point to input validation failures or missing tooling.

Project resources and tools

The server demonstrates runtime validation and resource management for a practical learning setup. Tools and resources are designed to illustrate how an AI model can interact with external capabilities.

Available tools

echo

Echo back input text with validation to ensure it is a string and present

add_numbers

Add two numbers together with type checking to ensure numeric inputs

get_system_info

Return basic system information such as platform and architecture

validate_email

Validate email addresses using schema-based validation