MCP Server Starter
A basic structure to build and run local tools that support the Model Context Protocol (MCP) standard, compatible with AI tools like Cursor and Claude.
README
MCP Server Starter

<div align="center"> <!-- <img alt="NPM Downloads" src="https://img.shields.io/npm/instructa/mcpn?style=flat-square&logo=npm"> <img alt="jsDelivr hits (npm)" src="https://img.shields.io/jsdelivr/npm/instructa/mcpn?style=flat-square&logo=jsdeliver"> <img alt="GitHub Sponsors" src="https://img.shields.io/github/sponsors/instructa/mcpn?style=flat-square&logo=github"> <br /> --> <strong>Created by</strong><br /> <a href="https://twitter.com/kregenrek"> <img src="https://img.shields.io/twitter/follow/kregenrek?style=social" alt="Follow @kregenrek on Twitter"> </a> </div>
Want to build your own MCP server?
MCP Server Starter gives you a basic structure to run local tools with Cursor, Claude, and others using the MCP standard.
<a href="https://glama.ai/mcp/servers/@instructa/mcp-starter"> <img width="380" height="200" src="https://glama.ai/mcp/servers/@instructa/mcp-starter/badge" alt="Starter MCP server" /> </a>
Features
-
📡 Flexible Communication
- Supports multiple communication protocols between client and server,
stdio: Local usageStreamable HTTP: Remote and local useagesse: Remote and local usage (deprecated)~~
-
📦 Minimal Setup - Get started quickly with a basic server implementation.
-
🤖 Cursor AI Integration - Includes example
.cursor/mcp.jsonconfiguration. -
⌨️ TypeScript - Add type safety to your project.
Todo
- [ ] Add option to publish your own packages
- [ ] Better CLI support for scaffolding
- [ ] Prompts to build tools on the fly
Getting Started
Prerequisites
Usage
Supported Transport Options
Model Context Protocol Supports multiple Transport methods.
stdio

Recommend for local setups
Code Editor Support
Add the code snippets below
- Cursor:
.cursor/mcp.json
Local development/testing
Use this if you want to test your mcp server locally
{
"mcpServers": {
"my-starter-mcp-stdio": {
"command": "node",
"args": ["./bin/cli.mjs", "--stdio"]
}
}
}
Published Package
Use this when you have published your package in the npm registry
{
"mcpServers": {
"my-starter-mcp-stdio": {
"command": "npx",
"args": ["my-mcp-server", "--stdio"]
}
}
}
Streamable HTTP

Important: Streamable HTTP is not supported in Cursor yet
Recommend for remote server usage
Important: In contrast to stdio you need also to run the server with the correct flag
Local development
Use the streamable http transport
- Start the MCP Server Run this in your terminal
node ./bin/cli.mjs --http --port 4200
Or with mcp inspector
npm run dev-http
# npm run dev-sse (deprecated)
- Add this to your config
{
"mcpServers": {
"my-starter-mcp-http": {
"command": "node",
"args": ["./bin/cli.mjs", "--http", "--port", "4001"]
// "args": ["./bin/cli.mjs", "--sse", "--port", "4002"] (or deprecated sse usage)
}
}
}
Published Package
Use this when you have published your package in the npm registry
Run this in your terminal
npx my-mcp-server --http --port 4200
# npx my-mcp-server --sse --port 4201 (deprecated)
{
"mcpServers": {
"my-starter-mcp-http": {
"url": "http://localhost:4200/mcp"
// "url": "http://localhost:4201/sse"
}
}
}
Use the Inspector
Use the inspect command to debug your mcp server

Command-Line Options
Protocol Selection
| Protocol | Description | Flags | Notes |
|---|---|---|---|
stdio |
Standard I/O | (None) | Default |
http |
HTTP REST | --port <num> (def: 3000), --endpoint <path> (def: /mcp) |
|
sse |
Server-Sent Events | --port <num> (def: 3000) |
Deprecated |
License
This project is licensed under the MIT License - see the LICENSE file for details.
Courses
- Learn to build software with AI: instructa.ai
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.