MCP Server Boilerplate
A starter template for building MCP (Model Context Protocol) servers. This boilerplate provides a clean foundation for creating your own MCP server that can integrate with Claude Desktop, Cursor, Claude Code, Gemini, and other MCP-compatible AI assistants.
Purpose
This boilerplate helps you quickly start building:
Custom tools for AI assistants
Resource providers for dynamic content
Prompt templates for common operations
Integration points for external APIs and services
Features
Two example tools: "hello-world" and "get-mcp-docs"
TypeScript support with ES2022 target and ES modules
Multi-client installation scripts (Claude Desktop, Cursor, Claude Code, Gemini, etc.)
Automatic npm publishing workflow
Environment variable support via
.env.local
Clean project structure with Zod validation
How It Works
This MCP server template provides:
A basic server setup using the MCP SDK
Example tool implementation
Build and installation scripts
TypeScript configuration for development
The included example demonstrates how to create a simple tool that takes a name parameter and returns a greeting.
Getting Started
Option 1: Use the Published Package (Recommended)
You can use this MCP server directly without cloning:
Option 2: Customize and Develop
Installation Scripts
This boilerplate includes convenient installation scripts for different MCP clients:
These scripts will:
Build the project automatically (TypeScript compilation + chmod permissions)
Configure clients to use
npx @r-mcp/<directory-name>@latest
(auto-updating)Only the local
.mcp.json
uses the development version (node dist/index.js
)Include environment variables from
.env.local
if present
Publishing Your Server
To publish your customized MCP server:
This script (scripts/build-and-publish.js
) will:
Commit any pending changes first
Update package name to
@r-mcp/<directory-name>
Update bin name to match directory
Increment patch version automatically
Build the TypeScript project
Commit version bump to git
Push to remote repository
Publish to npm with public access
Usage with MCP Clients
The installation scripts automatically configure your MCP clients. For reference, here's what gets added:
Production Clients (Claude Desktop, Cursor, Claude Code, Gemini):
Local Development (.mcp.json
):
After running installation scripts, restart your MCP client to connect to the server.
Customizing Your Server
Adding Tools
Tools are functions that the AI assistant can call. Here's the basic structure:
Adding Resources
Resources provide dynamic content that the AI can access:
Adding Prompts
Prompts are reusable templates:
Project Structure
Development Workflow
Local Development
Make changes to
src/index.ts
Run
pnpm run build
to compile TypeScriptTest your server with
pnpm start
Use
pnpm run install-mcp
for local testingRestart your MCP client to load changes
Publishing Updates
Test your changes locally
Run
pnpm run release
to publish to npmClients using
npx @r-mcp/<your-package>@latest
auto-updateNo client reconfiguration needed
Environment Variables
Create a .env.local
file for environment-specific configuration:
These variables are automatically included in MCP server configurations during installation.
Next Steps
Fork or clone this boilerplate
Customize the server name and tools in
src/index.ts
Add your own tools, resources, and prompts
Configure environment variables in
.env.local
Run
pnpm run release
to publish your serverInstall to clients with
pnpm run install-server
License
MIT
This server cannot be installed
remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
A starter template for building custom MCP servers that can integrate with Claude Desktop, Cursor, and other AI assistants. Provides example tools, TypeScript support, and automated publishing workflows to help developers create their own AI assistant integrations.
Related MCP Servers
- AsecurityFlicenseAqualityA starter template for building Model Context Protocol servers that can be integrated with Cursor or Claude Desktop, allowing developers to create custom tools and extensions for AI assistants.Last updated -1314
- AsecurityAlicenseAqualityA foundation for building custom local Model Context Protocol (MCP) servers that provide tools accessible to AI assistants like Cursor or Claude Desktop.Last updated -130MIT License
- -securityFlicense-qualityAn open source toolkit that converts 280+ integrations into MCP servers for use with Claude Desktop, Cursor, or Windsurf, enabling AI automation through a type-safe pieces framework written in TypeScript.Last updated -
- AsecurityFlicenseAqualityA starter template for building Model Context Protocol servers that integrate with AI assistants like Claude and Cursor, providing custom tools, resource providers, and prompt templates.Last updated -2