MCP Base Server

A TypeScript MCP server template with modular tools, built-in validation, and a solid development workflow.

typescript

0

GitHub Stars

typescript

Language

6 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": {
    "yone-k-mcp-base": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "mcp-base"
      ],
      "env": {
        "API_KEY": "YOUR_API_KEY_HERE",
        "LOG_LEVEL": "info"
      }
    }
  }
}

You set up a base MCP (Model Context Protocol) server in TypeScript to enable modular tool execution, built-in validation, and a solid development template. This base server helps you rapidly create MCP-enabled services, test tools locally, and connect with MCP clients that coordinate tool execution via a consistent interface.

How to use

Use an MCP client to connect to the base server and run tools you add to the project. You can run the server locally for development, or deploy it via a container. The base server is designed for quick experimentation with modular tools, robust error handling, and fast iteration during development.

How to install

Prerequisites you need before getting started are Node.js and Docker. You will also rely on npm to manage dependencies and run development commands.

# Prerequisites
# Install Node.js from https://nodejs.org/
# Install Docker from https://www.docker.com/

# Optional: install Docker Compose if you plan to use it

# Clone the base MCP project
# (Replace <repository-url> with the actual URL you are using)
git clone <repository-url>
cd mcp-base

# Install dependencies
npm install

# Build the project
npm run build

# Start in development mode
npm run dev

Additional setup and configuration

You can run and test the MCP server in several ways. The following examples show common approaches, including running via Docker, starting a local build, and running in development mode. If you need to expose environment variables or customize the command line, configure them as shown in the examples.

Tool implementation example

A complete tool implementation follows the provided template. This demonstrates how input/output schemas and the tool definition are structured so you can add your own tools later.

Available tools

my_tool

Demo tool that processes input and returns a structured output with a timestamp to demonstrate tool execution and schema validation.